# API Document for Pronunciation Assessment

# Description of the Interface

# It is a programming interface to evaluate the pronunciation level, identify pronunciation errors and defects, as well as analyze problems automatically through the intelligent speech recognition technology. The core technologies involved are mainly divided into two parts, i.e. the automatic assessment technology for Mandarin Chinese pronunciation level, and the automatic assessment technology for English pronunciation level.
  1. To get the authentication code: Apply for APPID from the iFLYTEK Open Platform, and add (streaming interface) to get interface keys APIKey and APISecret
  1. To integrate Websocket interface: common interface + parameter description, there may be differences between Chinese test question formats and English test question formats. Please refer to the Description about Test Question Formats for details.

# Interface Demos

# Please click Here (opens new window) to download demos. At present, only the demos for certain development languages are provided. For other languages, please carry out the development referring to the interface document below. We welcome developers to visit our community on Github (opens new window) and share your demos therein.

# Requirements for the Interface

Content Description
Request Protocol ws[s](wss is strongly recommended for improving the security)
Request URL wss://ise-API.xfyun.cn/v2/open-ise
Interface Authentication Signature mechanism, refer to Interface Authentication below for details.
Development Language Any language which allows to make Websocket requests for iFLYTEK cloud services.
Audio Attributes Sampling rate :16k; Bit length: 16bit; mono
Audio Format pcm, wav, mp3(the value of aue needs to be changed to lame)speex-wb;7
Language Chinese and English

# Interface Calling Flow

  1. Parameter upload, see the Description of Business Parameters for details:

The first parameter upload, data.status=0, and when parameter cmd=ssb, the parameter upload is completed.

  1. Audio upload

Start audio upload, set cmd=auw;

Set aus=1 for the first frame of audio;aus=2 for the intermediate frame of audio;and aus=4 for the last frame of audio,and set data.status=2.

Interface Authentication

In the handshake phase, the requester is required to sign the request, and the server-side verifies the validity of the request through the signature.

Authentication Method

Add authentication-related parameters after the request URL. Sample URL:

Authentication Parameters:

Parameter Type Required Description Sample
host string Yes Request host ise-API.xfyun.cn
date string Yes Current timestamp,RFC1123 format Fri, 18 Jan 2019 07:21:29 UTC
authorization string Yes Message related to the signature encoded with base64 (the signature is calculated based on hmac-sha256). Refer to the Rules for Generation of Authorization Parameters below

Detailed Rules for Generation of Authorization Parameters

# 1)Get interface keys APIKey and APISecret。

They are both 32-bit strings and can be viewed after creating a WebAPI platform application and adding voice dictation (stream version) service at the console of the iFLYTEK Open Platform.

  1. The format of the parameter authorization before encoded with base64 (authorization origin) is as follows.

Where, API_key is the APIKey got from the console, algorithm is an encryption algorithm (supports hmac-sha256 only), and headers are parameters participating in signature (see the notes below).

Signature is a string which is base64-encoded after using the encryption algorithm to sign the parameters participating in signature, see below for details.

Notes: headers are the parameters participating in signature. Please note that they are fixed parameter names("host date request-line"), instead of the values of these parameters.

3)The rules for the original field of signature (signature origin) are as follows:

The original field of signature is composed of three parameters, i.e. host, date and request-line which are concatenated in a certain format. The concatenation format is (\n is a new line character, ’:’ is followed by a space):

Suppose:

Then, the original field of signature (signature_origin) is:

4)Sign the signature origin using the hmac-sha256 algorithm in combination with APISecret, to obtain the signed summary, i.e. signature_sha.

Where, APISecret is the APISecret got from the console.

5)Encode the signature_sha with base64 to get the final signature.

Suppose:

Then, signature is

6)According to the above information, concatenate the string of authorization before it is encoded with base64(authorization origin). See the example below.

Notes: headers are the parameters participating in signature. Please note that they are fixed parameter names ("host date request-line"), instead of the values of these parameters.

7)Finally, encode the authorization origin with base64 to get the authorization parameter.

Examples of Authentication URL (Java)

Authentication Results

# If the handshake succeeds, an HTTP 101 status code will be returned, indicating that the protocol upgrade is successful; if the handshake fails, different HTTP Code status codes will be returned, depending on the type of the error, along with the error message. See the detailed description of errors in the table below.
HTTP Code Description Error Message Solution
401 authorization parameters are not available. {“message”:”Unauthorized”} Check if authorization parameters are available.
401 The parsing of signature parameters fails. {“message”:”HMAC signature cannot be verified”} Check if each signature parameter is available and correct, and if the copied API_key is correct.
HTTP Code Description Error Message Solution
401 Signature authentication fails. {“message”:”HMAC signature does not match”} The signature authentication fails, which may be caused by many possible reasons. 1. Check if API_key,API_secret is correct 2. Check if the parameters, i.e. host,date and request-line required for the calculation of signature are concatenated according to the protocol requirements. 3. Check if the base64 length of signature is normal (44 bytes normally).
403 Authentication of clock skew fails. {“message”:”HMAC signature cannot be verified, a valid date or x-date header is required for HMAC Authentication”} Check if the server time is standard. This error is reported when the deviation is more than 5 minutes.
403 Authentication of IP Whitelist fails. {"message":"Your IP address is not allowed"} The IP whitelist may be disabled on the console, or check whether the IP address set in the IP whitelist is the WAN IP address of the current machine.

Example of returned messages upon failure of handshake:

Interface Data Transmitting and Receiving

After the handshake succeeds, the Websocket connection will be established between the client and the server-side, through which, the client can upload and receive data simultaneously.

  1. The websocket-version supported by the server-side is 13. Ensure the framework used by the client supports this version.
  1. The type of all frames returned by the server-side is TextMessage, which corresponds to opcode = 1 in the protocol frame of the native websocket. Please ensure that the frame type parsed by the client must be this type. Otherwise, try to upgrade the client frame version or replace the technical framework.
  1. If there is a framing problem, namely, a json data packet is returned to the client by multiple frames, causing the client’s failure in parsing the json. In most cases, this is because the client’s framework has a problem in parsing the websocket protocol. Therefore, try to upgrade the framework version first, or replace the technical framework in the event of this problem.
  1. If it is necessary to close the connection after the client session is over, try to ensure that the websocket error code sent to the server-side is 1000 (ignore this requirement if the client framework is not provided with an interface for sending the error code upon closing of the session).

Request Parameters

All the request data is json string.

Parameter Type Required Description
common object Yes Common parameter, which is only uploaded during the first frame request after a successful handshake. See below for more information.
business object Yes Business parameter, which is only uploaded during the first frame request after a successful handshake. See below for more information.
data object Yes Business data stream parameter, which should be uploaded during all requests after a successful handshake. See below for more information.

Description of Common Parameters(common)

Parameter Type Required Description
app_id string Yes appid message applied from the platform

Description of Business Parameters(business)

Parameter Type Required Description Example
sub string Yes Service type is specified as Ise (open evaluation) ise
ent string Yes Chinese:cn_vip English:en_vip cn_vip
Parameter Type Required Description Example
category string Yes Chinese question types: read_syllable(individual character reading, special for Chinese) read_word(word reading) read_sentence(sentence reading) read_chapter(chapter reading) English question types: read_word(word reading) read_sentence(sentence reading) read_chapter(chapter reading) simple_expression(English situational expression) free_reading(English text-free reading) read_choice(English choice question) topic(English free-answer question) retell(English retelling question) picture_talk(English picture-talk) oral_translation(English oral translation) read_sentence
aus int Yes To distinguish audio status during audio upload during audio upload Take the value according to upload stage
during audio upload 1:First frame of audio 2:Intermediate audio 4:Last frame of audio
cmd string Yes Used to distinguish data upload stages ssb: parameter uploading stage ttp:text uploading stage (When ttp_skip=true, this stage may be skipped,and the text in the text field may be used directly) auw: audio uploading stage Take the value according to upload stage
text string Yes utf8 code of the text to be evaluated, it needs to be added with utf8bom header '\uFEFF'+text
tte string Yes Codebook of the text to be evaluated utf-8 gbk utf-8
ttp_skip bool Yes Skip ttp and directly use the text in ssb for evaluation (check by combining with cmd parameter during use), the default value is true true
Parameter Type Required Description Example
extra_ability string No Extra ability(valid condition ise_unite=1, rst value is not equal to plain); multi-dimension score display (accuracy score, fluency score, and integrity score)display extra_ability value is multi_dimension(applicable to characters, words, sentences and chapters, and; if multiple abilities are selected, they should be separated by a semicolon); Word pitch information display (pitch beginning value, and ending value)extra_ability value is pitch, only applicable to word and sentence question types; Phoneme error information display(whether the phone and tone are correct) extra_ability value is syll_phone_err_msg(applicable to characters, words, sentences and chapters, if multiple abilities are selected, they should be separated by a semicolon) multi_dimension
aue string No Audio format raw: uncompressed audio in pcm format or in wav lame:mp3 format speex-wb;7 audio in iFLYTEK open source speex format (default) raw
auf string No Audio sampling rate Default:audio L16;rate=16000 audio L16;rate=16000
rstcd string No Returned result format utf8 gbk (default) utf8
group string No Audio scoring results for the same test paper are different, depending on target population(only Chinese characters, words, and sentences are supported), this parameter will affect the accuracy score adult(adult,if no population is set, adult is default) youth(middle school, the effect is the same as that when pupil parameter is set) pupil(elementary school) adult
check_type string No Set the evaluation score and thresholds for error detection (Only supported by English engines) easy; common; Hard. common
Parameter Type Required Description Example
grade string No Set learning stage parameters for the evaluation (only Chinese question types: sentence and chapter question types for middle and elementary schools are supported) junior (Grades1 and 2) middle (Grades 3 and 4) senior(Grades 5 and 6) middle
auto_tracking string No Reading tracking enable; disable(default) disable
garbage_roll_back String No Garbage rollback of reading tracking (enable should be configured when reading tracking is used) enable; disable (default) disable
track_type string No Tracking mode: hard(skipping-in-reading is not supported, as it is likely to be followed timely) easy(skipping-in-reading supported) easy
rst string No Control of evaluation result level and scoring system: entirety(default); plain. entirety
ise_unite string No Control of scoring system and returned results 0:No control(default) (when ise_unite=0, rst!=plain transmits plev=1 or plev=2 will change into 5-score system) 1:Control(in the case of ise_unite=1, only when English is rst!=plain, can the 100-score system be used) 1
plev string No In the case of ise_unite=0, plev:1(part of node information is deleted) plev:2 or plev:0(all information is given) 0
# Examples of request parameters:

First data sending:

Request data audio parameter(data)

Parameter Type Required Description Example
data string Yes Audio data, encoded with base64(if the audio in wav format is used, the header should be removed)) Audio data, used as the value after encoded with base64
status string Yes Status of the sent data , it is 0 for the first time, 1 for the intermediate data and 2 for the last time Change the value according to the status of the sent data

Subsequent data sending

Returned Parameters

Description of Returned Parameters of Request Data Audio

Returned Parameter Type Description
code int Returned code,0 means the request is successful; any other error code means failure of request, the client should immediately stop the connection and end the session in this case. Refer to Error Codes for the detailed list of error codes.
message string Specific error description upon occurrence of error
data object Returned data
data.data string Evaluation result,base64 string,in xml format after parsed
status int Status of returned results,when status=2,it means that all results are returned. The client should take the result when status=2 as the final result.

Examples of Returns:

{

"code": 0,

"message": "success",

"sid": "isexxxxxxxxxxxxxxxxxxxxxxxxx", "data": {

"status": 2,

"data": "PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iVVRGLTgiPz4KICA8eG1sX3Jlc3VsdD4KICAgICA gPHJlYWRfc2VudGVuY2UgbGFuPSJjbiIgdHlwZT0ic3R1ZHkiIHZlcnNpb249IjcsMCwwLDEwMjQiPgo gICAgICAgICAgPHJlY19wYXBlcj4KICAgICAgICAgICAgICA8cmVhZF9zZW50ZW5jZSBhY2N1cmFjeV9

zY29yZT0iMTAwLjAwMDAwMCIgYmVnX3Bvcz0iMCIgY29udGVudD0i5LuK5aSp5aSp5rCU5oCO5LmI5qC 344CCIiBlbW90aW9uX3Njb3JlPSI4Ny4zMTUzNjEiIGVuZF9wb3M9IjE1MCIgZXhjZXB0X2luZm89IjA iIGZsdWVuY3lfc2NvcmU9Ijg3LjYyMDMwMCIgaW50ZWdyaXR5X3Njb3JlPSIxMDAuMDAwMDAwIiBpc19 yZWplY3RlZD0iZmFsc2UiIHBob25lX3Njb3JlPSIxMDAuMDAwMDAwIiB0aW1lX2xlbj0iMTUwIiB0b25 lX3Njb3JlPSIxMDAuMDAwMDAwIiB0b3RhbF9zY29yZT0iOTIuNTExMjAwIj4KICAgICAgICAgICAgICA gICAgPHNlbnRlbmNlIGJlZ19wb3M9IjAiIGNvbnRlbnQ9IuS7iuWkqeWkqeawlOaAjuS5iOagtyIgZW5 kX3Bvcz0iMTUwIiBmbHVlbmN5X3Njb3JlPSIwLjAwMDAwMCIgcGhvbmVfc2NvcmU9IjEwMC4wMDAwMDA iIHRpbWVfbGVuPSIxNTAiIHRvbmVfc2NvcmU9IjEwMC4wMDAwMDAiIHRvdGFsX3Njb3JlPSI4Ni45NTk 5ODQiPgogICAgICAgICAgICAgICAgICAgICAgPHdvcmQgYmVnX3Bvcz0iMCIgY29udGVudD0i5LuKIiB lbmRfcG9zPSIyMiIgc3ltYm9sPSJqaW4xIiB0aW1lX2xlbj0iMjIiPgogICAgICAgICAgICAgICAgICA gICAgICAgIDxzeWxsIGJlZ19wb3M9IjAiIGNvbnRlbnQ9ImZpbCIgZHBfbWVzc2FnZT0iMzIiIGVuZF9 wb3M9IjEiIHJlY19ub2RlX3R5cGU9ImZpbCIgdGltZV9sZW49IjEiPgogICAgICAgICAgICAgICAgICA gICAgICAgICAgICA8cGhvbmUgYmVnX3Bvcz0iMCIgY29udGVudD0iZmlsIiBkcF9tZXNzYWdlPSIzMiI gZW5kX3Bvcz0iMSIgcmVjX25vZGVfdHlwZT0iZmlsIiB0aW1lX2xlbj0iMSI+PC9waG9uZT4KICAgICA gICAgICAgICAgICAgICAgICAgICA8L3N5bGw+CiAgICAgICAgICAgICAgICAgICAgICAgICAgPHN5bGw

gYmVnX3Bvcz0iMSIgY29udGVudD0i5LuKIiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9zPSIyMiIgcmVjX25 vZGVfdHlwZT0icGFwZXIiIHN5bWJvbD0iamluMSIgdGltZV9sZW49IjIxIj4KICAgICAgICAgICAgICA gICAgICAgICAgICAgICAgPHBob25lIGJlZ19wb3M9IjEiIGNvbnRlbnQ9ImoiIGRwX21lc3NhZ2U9IjA iIGVuZF9wb3M9IjQiIGlzX3l1bj0iMCIgcGVycl9sZXZlbF9tc2c9IjIiIHBlcnJfbXNnPSIwIiByZWN fbm9kZV90eXBlPSJwYXBlciIgdGltZV9sZW49IjMiPjwvcGhvbmU+CiAgICAgICAgICAgICAgICAgICA gICAgICAgICAgIDxwaG9uZSBiZWdfcG9zPSI0IiBjb250ZW50PSJpbiIgZHBfbWVzc2FnZT0iMCIgZW5 kX3Bvcz0iMjIiIGlzX3l1bj0iMSIgbW9ub190b25lPSJUT05FMSIgcGVycl9sZXZlbF9tc2c9IjEiIHB lcnJfbXNnPSIwIiByZWNfbm9kZV90eXBlPSJwYXBlciIgdGltZV9sZW49IjE4Ij48L3Bob25lPgogICA gICAgICAgICAgICAgICAgICAgICAgIDwvc3lsbD4KICAgICAgICAgICAgICAgICAgICAgIDwvd29yZD4 KICAgICAgICAgICAgICAgICAgICAgIDx3b3JkIGJlZ19wb3M9IjIyIiBjb250ZW50PSLlpKkiIGVuZF9

wb3M9IjQwIiBzeW1ib2w9InRpYW4xIiB0aW1lX2xlbj0iMTgiPgogICAgICAgICAgICAgICAgICAgICA gICAgIDxzeWxsIGJlZ19wb3M9IjIyIiBjb250ZW50PSLlpKkiIGRwX21lc3NhZ2U9IjAiIGVuZF9wb3M 9IjQwIiByZWNfbm9kZV90eXBlPSJwYXBlciIgc3ltYm9sPSJ0aWFuMSIgdGltZV9sZW49IjE4Ij4KICA gICAgICAgICAgICAgICAgICAgICAgICAgICAgPHBob25lIGJlZ19wb3M9IjIyIiBjb250ZW50PSJ0IiB

kcF9tZXNzYWdlPSIwIiBlbmRfcG9zPSIzMCIgaXNfeXVuPSIwIiBwZXJyX2xldmVsX21zZz0iMSIgcGV ycl9tc2c9IjAiIHJlY19ub2RlX3R5cGU9InBhcGVyIiB0aW1lX2xlbj0iOCI+PC9waG9uZT4KICAgICA gICAgICAgICAgICAgICAgICAgICAgICAgPHBob25lIGJlZ19wb3M9IjMwIiBjb250ZW50PSJpYW4iIGR

wX21lc3NhZ2U9IjAiIGVuZF9wb3M9IjQwIiBpc195dW49IjEiIG1vbm9fdG9uZT0iVE9ORTEiIHBlcnJ fbGV2ZWxfbXNnPSIxIiBwZXJyX21zZz0iMCIgcmVjX25vZGVfdHlwZT0icGFwZXIiIHRpbWVfbGVuPSI xMCI+PC9waG9uZT4KICAgICAgICAgICAgICAgICAgICAgICAgICA8L3N5bGw+CiAgICAgICAgICAgICA gICAgICAgICA8L3dvcmQ+CiAgICAgICAgICAgICAgICAgICAgICA8d29yZCBiZWdfcG9zPSI0MCIgY29

udGVudD0i5aSpIiBlbmRfcG9zPSI1OCIgc3ltYm9sPSJ0aWFuMSIgdGltZV9sZW49IjE4Ij4KICAgICA gICAgICAgICAgICAgICAgICAgICA8c3lsbCBiZWdfcG9zPSI0MCIgY29udGVudD0i5aSpIiBkcF9tZXN zYWdlPSIwIiBlbmRfcG9zPSI1OCIgcmVjX25vZGVfdHlwZT0icGFwZXIiIHN5bWJvbD0idGlhbjEiIHR pbWVfbGVuPSIxOCI+CiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIDxwaG9uZSBiZWdfcG9zPSI 0MCIgY29udGVudD0idCIgZHBfbWVzc2FnZT0iMCIgZW5kX3Bvcz0iNDYiIGlzX3l1bj0iMCIgcGVycl9 sZXZlbF9tc2c9IjEiIHBlcnJfbXNnPSIwIiByZWNfbm9kZV90eXBlPSJwYXBlciIgdGltZV9sZW49IjY iPjwvcGhvbmU+CiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIDxwaG9uZSBiZWdfcG9zPSI0NiI gY29udGVudD0iaWFuIiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9zPSI1OCIgaXNfeXVuPSIxIiBtb25vX3R vbmU9IlRPTkUxIiBwZXJyX2xldmVsX21zZz0iMSIgcGVycl9tc2c9IjAiIHJlY19ub2RlX3R5cGU9InB hcGVyIiB0aW1lX2xlbj0iMTIiPjwvcGhvbmU+CiAgICAgICAgICAgICAgICAgICAgICAgICAgPC9zeWx sPgogICAgICAgICAgICAgICAgICAgICAgPC93b3JkPgogICAgICAgICAgICAgICAgICAgICAgPHdvcmQ gYmVnX3Bvcz0iNTgiIGNvbnRlbnQ9IuawlCIgZW5kX3Bvcz0iNzQiIHN5bWJvbD0icWk5IiB0aW1lX2x lbj0iMTYiPgogICAgICAgICAgICAgICAgICAgICAgICAgIDxzeWxsIGJlZ19wb3M9IjU4IiBjb250ZW5 0PSLmsJQiIGRwX21lc3NhZ2U9IjAiIGVuZF9wb3M9Ijc0IiByZWNfbm9kZV90eXBlPSJwYXBlciIgc3l tYm9sPSJxaTAiIHRpbWVfbGVuPSIxNiI+CiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIDxwaG9 uZSBiZWdfcG9zPSI1OCIgY29udGVudD0icSIgZHBfbWVzc2FnZT0iMCIgZW5kX3Bvcz0iNjYiIGlzX3l 1bj0iMCIgcGVycl9sZXZlbF9tc2c9IjEiIHBlcnJfbXNnPSIwIiByZWNfbm9kZV90eXBlPSJwYXBlciI gdGltZV9sZW49IjgiPjwvcGhvbmU+CiAgICAgICAgICAgICAgICAgICAgICAgICAgICAgIDxwaG9uZSB

iZWdfcG9zPSI2NiIgY29udGVudD0iaSIgZHBfbWVzc2FnZT0iMCIgZW5kX3Bvcz0iNzQiIGlzX3l1bj0 iMSIgbW9ub190b25lPSJUT05FMCIgcGVycl9sZXZlbF9tc2c9IjEiIHBlcnJfbXNnPSIwIiByZWNfbm9 kZV90eXBlPSJwYXBlciIgdGltZV9sZW49IjgiPjwvcGhvbmU+CiAgICAgICAgICAgICAgICAgICAgICA gICAgPC9zeWxsPgogICAgICAgICAgICAgICAgICAgICAgPC93b3JkPgogICAgICAgICAgICAgICAgICA gICAgPHdvcmQgYmVnX3Bvcz0iNzQiIGNvbnRlbnQ9IuaAjiIgZW5kX3Bvcz0iODQiIHN5bWJvbD0iemV uMyIgdGltZV9sZW49IjEwIj4KICAgICAgICAgICAgICAgICAgICAgICAgICA8c3lsbCBiZWdfcG9zPSI 3NCIgY29udGVudD0i5oCOIiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9zPSI4NCIgcmVjX25vZGVfdHlwZT0 icGFwZXIiIHN5bWJvbD0iemVuMyIgdGltZV9sZW49IjEwIj4KICAgICAgICAgICAgICAgICAgICAgICA gICAgICAgPHBob25lIGJlZ19wb3M9Ijc0IiBjb250ZW50PSJ6IiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9 zPSI3OSIgaXNfeXVuPSIwIiBwZXJyX2xldmVsX21zZz0iMSIgcGVycl9tc2c9IjAiIHJlY19ub2RlX3R 5cGU9InBhcGVyIiB0aW1lX2xlbj0iNSI+PC9waG9uZT4KICAgICAgICAgICAgICAgICAgICAgICAgICA gICAgPHBob25lIGJlZ19wb3M9Ijc5IiBjb250ZW50PSJlbiIgZHBfbWVzc2FnZT0iMCIgZW5kX3Bvcz0 iODQiIGlzX3l1bj0iMSIgbW9ub190b25lPSJUT05FMyIgcGVycl9sZXZlbF9tc2c9IjIiIHBlcnJfbXN nPSIwIiByZWNfbm9kZV90eXBlPSJwYXBlciIgdGltZV9sZW49IjUiPjwvcGhvbmU+CiAgICAgICAgICA gICAgICAgICAgICAgICAgPC9zeWxsPgogICAgICAgICAgICAgICAgICAgICAgPC93b3JkPgogICAgICA gICAgICAgICAgICAgICAgPHdvcmQgYmVnX3Bvcz0iODQiIGNvbnRlbnQ9IuS5iCIgZW5kX3Bvcz0iOTM iIHN5bWJvbD0ibWU1IiB0aW1lX2xlbj0iOSI+CiAgICAgICAgICAgICAgICAgICAgICAgICAgPHN5bGw gYmVnX3Bvcz0iODQiIGNvbnRlbnQ9IuS5iCIgZHBfbWVzc2FnZT0iMCIgZW5kX3Bvcz0iOTMiIHJlY19 ub2RlX3R5cGU9InBhcGVyIiBzeW1ib2w9Im1lMCIgdGltZV9sZW49IjkiPgogICAgICAgICAgICAgICA gICAgICAgICAgICAgICA8cGhvbmUgYmVnX3Bvcz0iODQiIGNvbnRlbnQ9Im0iIGRwX21lc3NhZ2U9IjA iIGVuZF9wb3M9Ijg4IiBpc195dW49IjAiIHBlcnJfbGV2ZWxfbXNnPSIxIiBwZXJyX21zZz0iMCIgcmV jX25vZGVfdHlwZT0icGFwZXIiIHRpbWVfbGVuPSI0Ij48L3Bob25lPgogICAgICAgICAgICAgICAgICA gICAgICAgICAgICA8cGhvbmUgYmVnX3Bvcz0iODgiIGNvbnRlbnQ9ImUiIGRwX21lc3NhZ2U9IjAiIGV uZF9wb3M9IjkzIiBpc195dW49IjEiIG1vbm9fdG9uZT0iVE9ORTAiIHBlcnJfbGV2ZWxfbXNnPSIxIiB wZXJyX21zZz0iMCIgcmVjX25vZGVfdHlwZT0icGFwZXIiIHRpbWVfbGVuPSI1Ij48L3Bob25lPgogICA gICAgICAgICAgICAgICAgICAgICAgIDwvc3lsbD4KICAgICAgICAgICAgICAgICAgICAgIDwvd29yZD4 KICAgICAgICAgICAgICAgICAgICAgIDx3b3JkIGJlZ19wb3M9IjkzIiBjb250ZW50PSLmoLciIGVuZF9 wb3M9IjE1MCIgc3ltYm9sPSJ5YW5nNCIgdGltZV9sZW49IjU3Ij4KICAgICAgICAgICAgICAgICAgICA

gICAgICA8c3lsbCBiZWdfcG9zPSI5MyIgY29udGVudD0i5qC3IiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9 zPSIxMTIiIHJlY19ub2RlX3R5cGU9InBhcGVyIiBzeW1ib2w9Inlhbmc0IiB0aW1lX2xlbj0iMTkiPgo gICAgICAgICAgICAgICAgICAgICAgICAgICAgICA8cGhvbmUgYmVnX3Bvcz0iOTMiIGNvbnRlbnQ9Il9 pIiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9zPSI5NiIgaXNfeXVuPSIwIiBwZXJyX2xldmVsX21zZz0iMSI gcGVycl9tc2c9IjAiIHJlY19ub2RlX3R5cGU9InBhcGVyIiB0aW1lX2xlbj0iMyI+PC9waG9uZT4KICA gICAgICAgICAgICAgICAgICAgICAgICAgICAgPHBob25lIGJlZ19wb3M9Ijk2IiBjb250ZW50PSJpYW5

nIiBkcF9tZXNzYWdlPSIwIiBlbmRfcG9zPSIxMTIiIGlzX3l1bj0iMSIgbW9ub190b25lPSJUT05FNCI gcGVycl9sZXZlbF9tc2c9IjEiIHBlcnJfbXNnPSIwIiByZWNfbm9kZV90eXBlPSJwYXBlciIgdGltZV9 sZW49IjE2Ij48L3Bob25lPgogICAgICAgICAgICAgICAgICAgICAgICAgIDwvc3lsbD4KICAgICAgICA gICAgICAgICAgICAgICAgICA8c3lsbCBiZWdfcG9zPSIxMTIiIGNvbnRlbnQ9InNpbCIgZHBfbWVzc2F nZT0iMCIgZW5kX3Bvcz0iMTUwIiByZWNfbm9kZV90eXBlPSJzaWwiIHRpbWVfbGVuPSIzOCI+CiAgICA gICAgICAgICAgICAgICAgICAgICAgICAgIDxwaG9uZSBiZWdfcG9zPSIxMTIiIGNvbnRlbnQ9InNpbCI gZW5kX3Bvcz0iMTUwIiB0aW1lX2xlbj0iMzgiPjwvcGhvbmU+CiAgICAgICAgICAgICAgICAgICAgICA gICAgPC9zeWxsPgogICAgICAgICAgICAgICAgICAgICAgPC93b3JkPgogICAgICAgICAgICAgICAgICA 8L3NlbnRlbmNlPgogICAgICAgICAgICAgIDwvcmVhZF9zZW50ZW5jZT4KICAgICAgICAgIDwvcmVjX3B hcGVyPgogICAgICA8L3JlYWRfc2VudGVuY2U+CiAgPC94bWxfcmVzdWx0Pg=="

}

}

Description of Returned Parameters of Chinese Assessment

Question Type Node Field Information
Chinese character and word question types (pupil, adult) read_syllable phone_score:phone score
or tone_score:tone score
read_wrod total_score:total score [(phone_score + tone_score)/2]
Chinese character and word question types (pupil, adult) sentence No important information
Chinese character and word question types (pupil, adult) word No important information
Chinese character and word question types (pupil, adult) syll dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced;
Chinese character and word question types(pupil, adult) phone dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced; mono_tone:tone
perr_level_msg: confidence of returned error detection results (a total of three numbers, i.e. 1,2,3, of which, 1 means the best, and 3 means the worst) is_yun:0 initial,1 final; When is_yun=0:perr_msg has two states:0 initial is correct ;1 initial is wrong;
When is_yun=1:perr_msg has four states: 0 final and tone are both correct; 1 final is wrong;2 tone is wrong;3 final and tone are both wrong;
Sentence and chapter question types (pupil) read_sentence or read_chapter accuracy_score:accuracy
emotion_score:overall impression score
fluency_score:fluency score integrity_score: integraty score phone_score:phone score tone_score:tone score
total_score:total score [total score = accuracy score_0.4 + fluency score _0.4
+ overall impression score *0.2]
Sentence and chapter question types (pupil) sentence phone_score:phone score tone_score:tone score total_score:total score [model regression]
Sentence and chapter question types (pupil) word No important information
Sentence and chapter question types (pupil) syll dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced;
Question Type Node Field Information
Sentence and chapter question types (Pupil) phone dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced; mono_tone:Tone
perr_level_msg: confidence of returned error detection results (a total of three numbers, i.e. 1,2,3, of which, 1 means the best, and 3 means the worst) is_yun:0 initial,1 final; When is_yun=0:perr_msg has two states:0 initial is correct ;1 initial is wrong; When is_yun=1:perr_msg has four states: 0 final and tone are both correct; 1 final is wrong;2 tone is wrong; 3 final and tone are both wrong;
Sentence and chapter question types (adult) read_sentence or read_chapter fluency_score:fluency score
integrity_score:integraty score phone_score:phone score tone_score:tone score
total_score:total score[model regression]
Sentence and chapter question types (adult) sentence phone_score:phone score tone_score:tone score total_score:total score[model regression]
Sentence and chapter question types (成人) word No important information
Sentence and chapter question types (adult) syll dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced;
Sentence and chapter question types (adult) phone dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back128
Replaced;
mono_tone:Tone
perr_level_msg: confidence of returned error detection results (a total of three numbers, i.e. 1,2,3, of which, 1 means the best, and 3 means the worst) is_yun:0 initial,1 final; When is_yun=0:perr_msg has two states:0 initial is correct ;1 initial is wrong; When is_yun=1:perr_msg has four states: 0 final and tone are both correct; 1 final is wrong;2 tone is wrong; 3 final and tone are both wrong;

Description Return Parameters of English Evaluation

Question Type Node Field Information
Word question type (adult, pupil) read_word [Adult word] total_score:total score[model regression] [Pupil word] total_score:total score[model regression]
Word question type (adult小 学) sentence No important information
Word question type word dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced; total_score:Score of each word
(adult, pupil)
Word question type (adult, pupil) syll syll_score:Score of each syllable
serr_msg:syllable error detection [1or 2049,indicating there is reading error; When serr_msg=2049,it indicates both the syllable and accent are wrong] syll_accent:accent error detection [if it is 0,indicating this syllable needs no accent, and the engine will perform detection;if it is 1, indicating the syllable needs accent and then parsed; When serr_msg= 2048 or 2049,it indicates reading is wrong]
Word question type (adult, pupil) phone dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced;
Sentence and chapter question types (adult, pupil) read_sentence accuracy_score:accuracy score
standard_score:standard score
fluency_score:fluency score
integrity_score:integraty score
[adult sentence]
total_score:total score = (0.5accuracy_score +
or fluency_score_0.3 + standard_score_0.2) integrity_score
read_chapter [adult chapter]
total_score:total score = (0.6accuracy_score +
fluency_score_0.3 + standard_score_0.1) integrity_score
[pupil sentence/pupil chapter]
total_score:total score = (0.7_accuracy_score +
fluency_score_0.3)* integrity_score
Sentence and chaper question types (adult, pupil) sentence accuracy_score:accuracy score
standard_score:standard score
fluency_score:fluency score
integrity_score:integraty score
[adult sentence]
total_score:total score = (0.5accuracy_score +
fluency_score_0.3 + standard_score_0.2) integrity_score
[adult chapter]
total_score:total score = (0.6accuracy_score +
fluency_score_0.3 + standard_score_0.1) integrity_score
[pupil sentence/pupil chapter]
total_score:total score = (0.7_accuracy_score +
fluency_score_0.3)* integrity_score
Question Type Node Field Information
Sentence and chaper question types (adult, pupil) word dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced; total_score:score of each word
Error detection for pause, continuous reading, rereading, rising and falling tone at the end of a sentence: 1. Conduct AND operation for the binary system of the Property value at word level in xml and the binary system of the Property value in the right table. 2. If the calculation result is equal to the Property value in the table above, it means that this type of detection has been performed here. If the calculation result is not equal to the Property value in the above table, it means that no detection has been performed here. 3. Determine whether werr_msg appears at the word level in xml, if it does not appear, it means reading is correct. 4. If it appears, perform the AND operation for the value of werr_msg in xml and the value corresponding to Werr_msg in the above table. If it is still equal to the value of this type, then it indicates there is an error in this type of reading.
Sentence and chaper question types (adult, pupil) syll syll_score:score of each syllable serr_msg:syllable error detection [1or 2049,indicating there is reading error]
Sentence and chaper question types(adult, pupil) phone dp_message:0 Normal;16 Missing-read;32 (Added-read);64 Read back; 128 Replaced;
Text-free reading rec_paper accuracy_score:accuracy score fluency_score:fluency score total_score:total score[accuracy_score + fluency_score)/2]
Situation expression rec_paper total_score:total score[model regression]
Story retelling- topic rec_paper total_score:total score[model regression]
Retelling, oral translation, key point question, picture-talk rec_paper accuracy_score:accuracy score standard_score:standard score fluency_score:fluency score integrity_score:integraty score total_score:total score[model regression]
Oral composition rec_paper total_score:total score[model regression]

Test Question Format Description

Chinese Test Question Format Description

Chinese Characters(read_syllable)

# Plain text examples:

(1)No header is required, and no Node name is included.

(2)The content that may be contained in the test paper: simplified Chinese characters, traditional Chinese characters (within the range of gbk), 0-9 Arabic numerals (not recommended), and separators.

(3)The separator is used between two characters, and no characters other than Chinese characters and spaces should appear at the beginning and end of the line.

(4)The paper content can contain 0-9 Arabic numerals, but it does not support that the paper content is all Arabic numerals. Numerical values and numeric strings with more than two digits(such as year, telephone number, time, etc.) are required to be expressed in Chinese numerals.

(5)The number of Chinese characters in one line should not exceed 100.

Pinyin marking examples:

(1)Use line breaks to separate Chinese characters.

(2)ü should be expressed as u, such as ju2(局) except for lü and nü which should be expressed as lv and nv(e.g. nv3(女)); and üe should be expressed as ue (lue4(略)).

(3)The Pinyin must be the correct Pinyin in the dictionary, and the value of Tone is taken between 0-9, where 0/5/6/7/8/9 all denote zeroth tone.

(4)Do not use Arabic numerals in Chinese characters.

(5)Each Chinese character in the test paper with Pinyin must be marked with Pinyin.

Note: The total number range of Chinese characters in the text of the test paper is (0,200], the total number range of characters is (0,5000), the recommended number range of Chinese characters in a text is (0,100), and the recommended number range of characters is (0,200].

Chinese Words(read_word)

# Plain text examples:

(1)The content that may be contained in the test paper: simplified Chinese characters, traditional Chinese characters (within the range of gbk), 0-9 Arabic numerals (not recommended), and separators.

(2)The separator is used between two words, and no characters other than Chinese characters and spaces should appear at the beginning and end of the line.

(3)The paper content can contain 0-9 Arabic numerals, but it does not support that the paper content is all Arabic numerals. Numerical values and numeric strings with more than two digits(such as year, telephone number, time, etc.) are required to be expressed in Chinese numerals.

(4)The number of Chinese characters in one line should not exceed 100.

Pinyin marking examples:

(1)Use line breaks to separate Chinese words.

(2)The content that may be contained in the test paper: simplified Chinese characters, Pinyin, and Pinyin separator (|)

(3)The Pinyin must be the correct Pinyin in the dictionary, and the value of Tone is taken between 0-9, where 0/5/6/7/8/9 all denote zeroth tone.

(4)Use the "|" symbol to separate the Pinyin of Chinese characters in a word.

(5)Do not use Arabic numerals in Chinese characters.

(6)Each Chinese character in the test paper with Pinyin must be marked with Pinyin.

Note: The total number range of Chinese characters in the text of the test paper is (0,200], the total number range of characters is (0,5000), the recommended number range of Chinese characters in a text is (0,100), and the recommended number range of characters is (0,200].

Chinese Sentences(read_sentence)

# Plain text examples:

(1)The content that may be contained in the test paper: simplified Chinese characters, traditional Chinese characters (within the range of gbk), 0-9 Arabic numerals (not recommended), and separators.

(2)The paper content can contain 0-9 Arabic numerals, but it does not support that the paper content is all Arabic numerals. Numerical values and numeric strings with more than two digits(such as year, telephone number, time, etc.) are required to be expressed in Chinese numerals.

(3)The number of Chinese characters in one line should not exceed 100.

Pinyin marking examples:

(1)Use line breaks to separate sentences。

(2)The content that may be contained in the test paper: simplified Chinese characters, Pinyin, and Pinyin separator (|)

(3)Do not use Arabic numerals, English words, or letters in the test paper.

(4)The Pinyin must be the correct Pinyin in the dictionary, and the value of Tone is taken between 0-9, where 0/5/6/7/8/9 all denote zeroth tone.

(5)Use the "|" symbol to separate the Pinyin in a sentence.

(6)The number of Chinese characters in one line should not exceed 100.

(7)Each Chinese character in the test paper with Pinyin must be marked with Pinyin.

Note: The total number range of Chinese characters in the text is (0,1000], the total number range of characters is (0,10000), the recommended number range of Chinese characters in a text is (5,500), and the recommended number range of characters is (0,1000].

Chinese Chapter(read_chapter)

# Plain text example (same as the sentence test paper, except that the chapter is composed of multiple sentences, please refer to the notes of the sentence test paper for detailed description):

Pinyin marking examples:

English Test Question Format Description

English Words(read_word)

# Common text:

(1)Necessary node: [word], use line breaks for separation.

(2)The number of words should not exceed 100.

(3)Word segmentation only supports tab, enter and space keys.

(4)Symbols that can be supported by words: English half-width characters.-‘(i.e. dot, hyphen, upper single quote), such as p.m and year-old are supported, while hello and world are not supported.

(5)Punctuation marks not supported by words: question mark, exclamation mark, semicolon, colon, comma, and illegal characters ( ) [.

(6)Do not write the punctuation mark as a single word in the test paper (namely, spaces are at both ends of the punctuation mark). Otherwise, an error will be reported.

Number reading method marking:

(1)The line below the number must be marked with [number_replace].

(2)In the next line of [number_replace], mark it in the format "number/reading/". Note that the number of symbol / must be 2, and no symbol should be added for the content in //.

Note: the content of [word]node should be free of any characters unrelated to the content of the word, otherwise the effect will be affected.

English Sentences(read_sentence)

# Common text:

(1)Necessary node: [content] ,use line breaks for separation.

(2)The content can be segmented into sentences with four English half-width characters, i.e. . ! ? ;

(3)The symbols ( ) [ should not appear before and in the text.

(4)The character [ should not appear at the end of the text, and only one (or ) is allowed to appear. More than one (or ) are prohibited.

(5)Full-width characters (a full-width character occupies two bytes, and the engine first converts full-width to half-width) are supported and their proportion in the total number of bytes of the entire contentNode content must not exceed 10%.

(6)It is not supported that the proportion of the characters in the total number of bytes of the entire contentNode content exceed 10%. Common unsupported characters include @ , # , $ , % , & , * , { , }, etc.

(7)The number of words in each sentence should not exceed 100, and the number of bytes in each sentence should not exceed 1024 bytes (the sentence segmentation symbol is also counted as one byte).

(8)The number of all words should not exceed 1000.

Supported English half-width characters:

Number reading method marking:

(1)The number of symbol / in a single word should be 2, otherwise an error will be reported.

(2)Multiple speechs of a number are separated by vertical bar "|".

(3)The content must be in lowercase letters.

(4)The maximum number of Replacement numbers should not exceed 31.

Note: Unless there is special requirement, it is prohibited to add any information unrelated with the paper content in the content text, or to change words (such as changing long to l-o-n-g), otherwise, the score will be affected.

Description of Unnecessary Node in Sentence Question Type:

(1)For [number_replace], if the number of the symbol / in a single word is not 2, an error will be reported.

(2)For [number_replace], if the Replacement content is null, an error will be reported (//).

(3)For [number_replace], multiple speechs of a number are separated by vertical bar "|".

(4)For [number_replace], the content must be in lowercase letters.

(5)For [number_replace], the maximum number of Replacement numbers should not exceed 31.

(6)For [vocabulary],if the number of the symbol / in a single word is not 2, an error will be reported.

(7)For [vocabulary],if the word phonetic symbol is null, an error will be reported (//).

(8)For [vocabulary],if the number of bytes of a single phonetic symbol exceeds 128*6 bytes, an error will be reported.

(9)For [vocabulary],multiple phonetic symbols may be separated by vertical bars.

(10)For [lmtext](this Node is not recommended),English half-width characters , . ! ? ; for sentence segmentation.

(11)For [lmtext](this Node is not recommended),the contents related to Node in the test paper (except vocabulary and number_replace Node) should be added to the LMText.

English Chapter(read_chapter)

# Test paper examples:

(1)Necessary node:[content],use line breaks for separation.

(2)The content can be segmented into sentences with four English half-width characters, i.e. . ! ? ;

(3)The symbols ( ) [should not appear before and in the text.

(4)The character [ should not appear at the end of the text, and only one (or ) is allowed to appear. More than one (or ) are prohibited.

(5)Full-width characters (a full-width character occupies two bytes, and the engine first converts full-width to half-width) are supported and their proportion in the total number of bytes of the entire contentNode content must not exceed 10%.

(6)It is not supported that the proportion of the characters in the total number of bytes of the entire contentNode content exceed 10%. Common unsupported characters include @ , # , $ , % , & , * , { , }, etc.

(7)The number of words in each sentence should not exceed 100, and the number of bytes in each sentence should not exceed 1024 bytes (the sentence segmentation symbol is also counted as one byte).

(8)The number of all words should not exceed 1000.

(9)Do not add meaningless character combinations, such as various combinations of numbers, letters and symbols, such as 7FH34J, into the text.

Note: Unless there is special requirement, it is prohibited to add any information unrelated with the paper content in the content text, or to change words (such as changing long to l-o-n-g), otherwise, the score will be affected.

English Situational Expression(simple_expression)

# Test paper examples:

(1)Necessary nodes:[choice], [keywords],use line breaks for separation.

(2)The content can be segmented into sentences with five English half-width characters, i.e. , . ! ? ;

(3)The serial number of each option should be consecutive, and the part between the serial number and the content should be arranged as "serial number + dot + space + content".

(4)Any option should be displayed in one line. If the content of a certain option is manually wrapped (except for automatic line wrapping by the system), resulting in that there no serial number in the second line, an error will be reported.

(5)The characters ( ) [ should not appear before and in the text of each choice option,an error will be reported.

(6)One (or) is allowed to appear at the end of the text of each choice option, but more than one (or) are prohibited.

(7)If full-width characters to the content of each choice option, make sure that their proportion in the number of bytes of each choiceNode content must not exceed 10%.

(8)To enter unsupported characters in each choice option, make sure that such characters account for no more than 10% of the number of bytes in each choiceNode content. Common unsupported characters are @, #, $,%, ^, &, *, +, =, {, }.

(9)The number of words(except symbols) in each choice option should not exceed 100.

(10)Unless there is special requirement, it is prohibited to add any character unrelated with the content in any of the choice options, otherwise, the marking and score will be affected.

W: I will give a speech next Wednesday in my English class, but I am not fully prepared yet. Can you give me some advice?

M: Sure. What's your topic?

W: Well, I am always concerned about environmental issues, so my topic is Environmental Protection.

M: This is a good topic, but it is too big. [question]

How can I handle this problem?

[macanswer]

You have to narrow down your topic. For example, you may talk about what college students can do to protect our environment. After that, you need to do some research to collect relevant information as much as possible. Then, you should organize your arguments well. Logical organization is very important.

[lmtext]

What should I do with the topic? How can I deal with the topic?

What can I do with the topic?

What should I do with this subject? How can I deal with this subject?

What can I do with this subject? What should I do with this title? How can I deal with this title?

What can I do with this title? What should I manage this title? How can I manage this title?

What can I manage this title?

What should I manage this subject? How can I manage this subject?

What should I manage this topic? How can I manage this topic?

What can I manage this topic?

How should I deal with this topic? How should I deal with this title? How should I deal with this subject?

Congratulations, Tom! You gave a wonderful speech yesterday morning. Thank you Mary.

I will give a speech next Wednesday in my English class, but I am not fully prepared yet. Can you give me some advice?

Sure. What's your topic?

Well, I am always concerned about environmental issues, so my topic is Environmental Protection.

This is a good topic, but it is too big.

You have to narrow down your topic. For example, you may talk about what college students can do to protect our environment. After that, you need to do some research to collect relevant information as much as possible. Then, you should organize your arguments well. Logical organization is very important.

Can you tell me how to do that? Can you tell me how?

Can you tell me what I can do? Can you tell me how to do it?

Can you tell me how I should do?

Can you tell me how to deal with it? Can you tell me how to manage that? Can you tell me how to manage it?

Can you tell me what to do?

Could you tell me how to do that? Could you tell what to do?

You need to see relationships among ideas clearly. You may use words like ""firstly"", ""secondly"" and ""thirdly"" to help you indicate the development of your ideas. Also, do remember to provide evidence for your arguments. For instance, data and research findings can make your speech more convincing. In order to give a good speech, you've also got to know some public speaking skills.

What are these skills? What skills?

What are those skills?

Well, there are so many. It is very important to have good control of the pace of your speech. Don't speak too fast or too slowly. Use appropriate body language to better express yourself. For example, standing straight and having eye contact with the audience will give an impression of self confidence.

Yesterday morning.

Tom gave his speech yesterday morning. He gave his speech yesterday morning. Tom gave his lecture yesterday morning. He gave his lecture yesterday morning. The topic is too big.

The topic is too broad. The topic is too general. The topic is very big.

The topic is very broad. The topic is very general. Very big.

Very broad. Very general.

The topic is too obscure. Too obscure.

To collect relevant information as much as possible. To collect related information as much as possible. To collect relative information as much as possible. Collect relevant information as much as possible.

Collect related information as much as possible. Collect relative information as much as possible. To collect relevant messages as many as possible. To collect related messages as many as possible. To collect relative messages as many as possible.

To gather relevant information as much as possible. To gather related information as much as possible. To gather relative information as much as possible. Gather relevant information as much as possible.

Gather related information as much as possible. Gather relative information as much as possible. To gather relevant messages as many as possible. To gather related messages as many as possible. To gather relative messages as many as possible. More convincing.

Convincing.

Data and research findings can make the speech more convincing. Make the speech more convincing.

Data and research findings can convince people. They can convince people.

Convince people.

Stand straight and have eye contact. Stand straight and keep eye contact. Stand straight and maintain eye contact. To stand straight and have eye contact.

English Text-free Reading(free_reading)

# Test paper examples:

(1)Necessary node:[topic],use line breaks for separation.

(2)The first line is the title of the retelling topic, and it must be written in the "Serial number + dot + space + content" format, such as 1. + topic. It must begin with 1, and the following parts should appear in sequence; note that the space should not be substituted by a tab key or any other character. The characters ( ) [ should not appear in the title. Besides, full-width characters are also not allowed in the title. Otherwise, an error will be reported.

(3)The second line is the content of the retelling topic, and it must also be written in the "Serial number + dot + space + content" format, such as 1.1. + content. It must begin with 1.1.; note that the space should not be substituted by a tab key or any other character.

(4)If the content covers multiple topics, then the serial number id must be consecutive, such as 1.1., 1.2., 1.3 and so on.

(5)The content can be segmented into sentences with five English half-width characters, i.e. , . ! ? ;

(6)Any option needs to be displayed in one line. If the content of a certain option is manually wrapped (except for automatic line wrapping by the system), resulting in that there is no serial number in the second line, an error will be reported.

(7)The number of the symbol / in a single word should be 2, otherwise an error will be reported.

English Choice Question(read_choice)

# Test paper example:

(1)Necessary nodes:[choice], [keywords],use line breaks for separation.

(2)The content can be segmented into sentences with five English half-width characters, i.e. , . ! ? ;

(3)The serial number of each option should be consecutive, and the part between the serial number and the content should be arranged as "serial number + dot + space + content".

(4)Any option should be displayed in one line. If the content of a certain option is wrapped, resulting in that there no serial number in the second line, an error will be reported.

(5)Each choice option can support full-width characters to occupy no more than 10% of the total bytes of the entire choiceNode content.

(6)The proportion of the unsupported characters of each choice option should exceed 10% of the total bytes of the choiceNode content.

(7)The content of keywords must be one of the choice options, and it must match the content of the correct option completely and continuously, and lack of any content is not allowed (different from the choiceNode restriction of the situation expression question type).

8)A answers to a single option can be segmented by five English half-width characters , . ! ? ; and multiple answers can be separated by vertical bars |.

(9)The number of words(except symbols) in each choice option should not exceed 100.

English Free-answer Question(topic)

# Test paper examples:

(1)Necessary Node:[topic],use line breaks for separation.

(2)The first line is the title of the retelling topic, and it must be written in the "Serial number + dot + space + content" format, such as 1. + topic. It must begin with 1, and the following parts should appear in sequence; note that the space should not be substituted by a tab key or any other character. The characters ( ) [ should not appear in the title. Besides, full-width characters are also not allowed in the title. Otherwise, an error will be reported.

(3)The second line is the content of the retelling topic, and it must also be written in the "Serial number + dot + space + content" format, such as 1.1. + content. It must begin with 1.1.; note that the space should not be substituted by a tab key or any other character.

(4)If the content covers multiple topics, then the serial number id must be consecutive, such as 1.1., 1.2., 1.3 and so on.

(5)The content can be segmented into sentences with five English half-width characters, i.e. , . ! ? ;

(6)Any option needs to be displayed in one line. If the content of a certain option is manually wrapped (except for automatic line wrapping by the system), resulting in that there is no serial number in the second line, an error will be reported.

(7)Unnecessary Node: [number_replace], [vocabulary], [lmtext], refer to the restrictions on unnecessary nodes of sentence question types for the standard description.

  1. Tom went to primary school in the countryside. Near his classroom, there was a small pond where two geese were raised.

  2. Students were all fond of them.

  3. One day, when Tom passed the school kitchen, he heard the cooks talking about killing the geese for the teachers' Christmas dinner.

  4. Tom got angry, and said to himself, ""I won't let them be eaten!"" That night, Tom worked out a plan. He was going to hide them somewhere far away from the school.

  5. The next morning, Tom went to school in his father's big coat. During the break, he rushed to the pond. Without anyone around, he caught the geese and pushed them inside the coat.

  6. However, the geese were larger than he had thought, and they tried very hard to free themselves from the coat. The big noise caught the notice of the head teacher and the students,

  7. They all ran to the pond.

  8. The head teacher asked for an explanation.

  9. Looking at the teacher with fear, Tom told the story and said, ""It is unfair to them. We all love them!""

  10. The head teacher smiled and promised not to have them killed for the Christmas dinner.

    [lmtext]

    The Goose Thief

Tom went to primary school in the countryside. Near his classroom, there was a small pond where two geese were raised. Students were all fond of them. One day, when Tom passed the school kitchen, he heard the cooks talking about killing the geese for the teachers' Christmas dinner. Tom got angry, and said to himself,

""I won't let them be eaten!"" That night, Tom worked out a plan. He was going to hide them somewhere far away from the school. The next morning, Tom went to school in his father's big coat. During the break, he rushed to the pond.

Without anyone around, he caught the geese and pushed them inside the coat. However, the geese were larger than he had thought, and they tried very hard to free themselves from the coat. The big noise caught the notice of the head teacher and the students, and they all ran to the pond. The head teacher asked for an explanation. Looking at the teacher with fear, Tom told the story and said, ""It is unfair to them. We all love them!"" The head teacher smiled and promised not to have them killed for the Christmas dinner.

English Retelling Question(retell)

# Test paper examples:

(1)Necessary nodes:[topic] , [keypoint],use line breaks for separation.

(2)The first line is the title of the retelling topic, and it must be written in the "Serial number + dot + space + content" format, such as 1. + topic. It must begin with 1, and the following parts should appear in sequence; note that the space should not be substituted by a tab key or any other character. The characters ( ) [ should not appear in the title. Besides, full-width characters are also not allowed in the title. Otherwise, an error will be reported.

(3)The second line is the content of the retelling topic, and it must also be written in the "Serial number + dot + space + content" format, such as 1.1. + content. It must begin with 1.1.; note that the space should not be substituted by a tab key or any other character.

(4)If the content covers multiple topics, then the serial number id must be consecutive, such as 1.1., 1.2., 1.3 and so on.

(5)The content can be segmented into sentences with five English half-width characters, i.e. , . ! ? ;

(6)Any option needs to be displayed in one line. If the content of a certain option is manually wrapped (except for automatic line wrapping by the system), resulting in that there is no serial number in the second line, an error will be reported.

(7)Unnecessary nodes: [number_replace], [vocabulary] and [lmtext], refer to the restrictions on unnecessary nodes of sentence question type for the standard description.

[topic]

  1. The Goose Thief

    1. Tom went to primary school in the countryside. Near his classroom, there was a small pond where two geese were raised. Students were all fond of them.

One day, when Tom passed the school kitchen, he heard the cooks talking about killing the geese for the teachers' Christmas dinner. Tom got angry, and said to himself, ""I won't let them be eaten!"" That night, Tom worked out a plan. He

was going to hide them somewhere far away from the school. The next morning, Tom went to school in his father's big coat. During the break, he rushed to the

pond. Without anyone around, he caught the geese and pushed them inside the coat. However, the geese were larger than he had thought, and they tried very hard to free themselves from the coat. The big noise caught the notice of the head teacher and the students, and they all ran to the pond. The head teacher asked for an explanation. Looking at the teacher with fear, Tom told the story and said, ""It is unfair to them. We all love them!"" The head teacher smiled and promised not to have them killed for the Christmas dinner.

[keypoint]

  1. Tom went to primary school in the countryside. Near his classroom, there was a small pond where two geese were raised.

  2. Students were all fond of them.

  3. One day, when Tom passed the school kitchen, he heard the cooks talking about killing the geese for the teachers' Christmas dinner.

  4. Tom got angry, and said to himself, ""I won't let them be eaten!"" That night, Tom worked out a plan. He was going to hide them somewhere far away from the school.

  5. The next morning, Tom went to school in his father's big coat. During the break, he rushed to the pond. Without anyone around, he caught the geese and pushed them inside the coat.

  6. However, the geese were larger than he had thought, and they tried very hard to free themselves from the coat. The big noise caught the notice of the head teacher and the students,

  7. They all ran to the pond.

  8. The head teacher asked for an explanation.

  9. Looking at the teacher with fear, Tom told the story and said, ""It is unfair to them. We all love them!""

  10. The head teacher smiled and promised not to have them killed for the Christmas dinner.

    [lmtext]

    The Goose Thief

Tom went to primary school in the countryside. Near his classroom, there was a small pond where two geese were raised. Students were all fond of them. One day, when Tom passed the school kitchen, he heard the cooks talking about killing the geese for the teachers' Christmas dinner. Tom got angry, and said to himself,

""I won't let them be eaten!"" That night, Tom worked out a plan. He was going to hide them somewhere far away from the school. The next morning, Tom went to school in his father's big coat. During the break, he rushed to the pond.

Without anyone around, he caught the geese and pushed them inside the coat. However, the geese were larger than he had thought, and they tried very hard to free themselves from the coat. The big noise caught the notice of the head teacher and the students, and they all ran to the pond. The head teacher asked for an explanation. Looking at the teacher with fear, Tom told the story and said, ""It is unfair to them. We all love them!"" The head teacher smiled and promised not to have them killed for the Christmas dinner.

English Picture-talk(picture_talk)

# Test paper example:

(1)Necessary node:[topic],use line breaks for separation. Refer to the [topic] restrictions on necessary nodes of story retelling question type for the standard description.

(2)Unnecessary nodes:[number_replace], [vocabulary] and [lmtext], Refer to the restrictions on unnecessary nodes of sentence question type for the standard description.

(3)For the unnecessary node[keypoint],the serial numbers should be consecutive,and the part between the serial number and the content should be arranged as "serial number + dot + space + content".

(4)For unnecessary node [keypoint],if there are multiple options under keypointNode,choose one of the options for segmentation.

[topic]

  1. Throw Litter

    1. Mary and her classmates went outing last weekend. Someone was flying kites, some people were having snacks. There were litters on the road. Mary picked up the waste bottles and paper the put them in the dustbin. The teacher praised

      Mary for her good deed.

    2. Last weekend, Mary went to the park with her classmates. They had a picnic in the park. Some people flew kites there. They had great fun there. Mary saw some rubbish on the road. She picked up the rubbish and threw it into the dustbin. The teacher praised Mary.

    3. Last Saturday, Mary's class went to the park. They brought some food and had a picnic on the grass. After that, they flew kites there. Suddenly, Mary found that there was some rubbish on the road. She then picked up the rubbish and threw it into the dustbin. Mary's teacher saw this. She said ""Well done"" to Mary. Mary was very happy.

    4. Mary went to the park with her friend last weekend. They had a picnic there, while some people were flying kites. Mary's friend wanted to fly a kite too. So she threw waste bottles and paper on the ground and ran away. Mary saw this and picked up the rubbish. Then she threw it into the garbage can. A woman noticed what Mary had done. She praised Mary for her good behavior.

    5. Mary went to the park to have a picnic with her friend last Sunday. They brought some juice and bread as lunch. After lunch, they joined other people to fly kites. Mary saw some waste bottles and paper on the ground. Someone threw them away after having a picnic. Mary cleaned the road, putting the garbage into a garbage can. A lady saw this and praised Mary for what she had done.

    6. Last weekend, Mary and her classmates went to the park. Some of them flew kites, and some of them had food on the grass. Mary brought some juice, bread and biscuits to share with her friend. After they finished eating, her friend

went to fly a kite. Mary gathered their waste bottles and paper and was about to threw them into the dustbin. Suddenly, she saw some garbage on the ground. She picked up the garbage, and threw it away with their waste bottles and paper. Her good behavior was noticed by the manager of the park. The manager praised her.

  1. Last weekend, Mary went outing with her classmates. Mary and her friend were having drinks and some bread. Others were flying kites or playing games. After a while, there were litters on the ground. Mary saw these and started to pick up all the waste paper and bottles. She put them into the dustbin. Mary's teacher praised her for what she had done.

    1. Mary went for an outing with her classmates last weekend. Some people played games and some people went to fly kites. Mary and Lily were having some snacks. When they were about to play, Mary noticed that there were litters around them. So she picked up the waste bottles and paper and threw them in the dustbin. Just then, her teacher saw it and praised Mary for what she did.

    2. The school held an outing last weekend. Mary and her classmates had fun there. Some people were playing games while some were flying kites. Mary and one of her classmates were having some snacks. Then, Mary found that there were some waste paper and bottles on the ground. So she threw all of them into the

      dustbin. At last, the ground became clean and Mary was praised by her teacher.

    3. Mary and her classmates went for an outing last weekend. They were very happy. Someone was flying kites, some were having food. After having lunch, they went on playing games. Mary noticed that there were some litters on the ground. So she picked up all the litters and then put them in the dustbin. Mary's good deed was saw by her teacher. The teacher praised Mary and felt proud of what she had done.

    4. Last Saturday, Mary's teacher took her class to an outing. The whole class were very happy then. Some people were flying kites while some were playing games. At lunch time, they had food and drank juice together. After that, there were some waste bottles and paper on the road. Mary started to pick them up and threw them into the dustbin. Her teacher saw it and spoke highly of what Mary

      had done. Mary felt very proud of herself.

    5. Last weekend Mary and her classmates went outing and had a picnic. Some people were flying kites, some people were having snacks. Suddenly, they found there was a lot of litter on the road. Mary picked up the waste bottles and paper the put them in the dustbin. The teacher praised Mary for her good behavior.

    6. Last weekend Mary went to the park with Some friends. Some of them were flying kites. Some friends were eating food. Suddenly, they saw there was some rubbish on the road. Mary picked up the rubbish and put it into the garbage. The teacher said Mary was good.

    7. Last weekend Mary went to the park. Some classmates were flying kites, some classmate were eating food. Suddenly, they saw there was a lot of rubbish

on the road. Mary picked up the rubbish and put it into the dustbin. The teacher said Mary was a good girl.

  1. Last weekend Mary had a picnic with her cousins in the park. Some were flying kites, some were eating food. They saw there was some litter on the road.

Mary picked up the litter and threw it into the dustbin. Her mother said Mary was good.

  1. Last weekend Mary had a picnic with her cousins in the park. Some flew kites, some ate food. Suddenly, they saw someone dropped a lot of litter on the road. Mary picked up the litter and threw it into the dustbin. Her mother said Mary did a good job.

    1. Last weekend, Mary went to the park for a picnic with her friend. They brought a lot of food and enjoyed it very much. Lily went to fly kite but she left many rubbish on the ground. Marry cleaned it and put it into the rubbish can. The teacher saw it and she said to Marry, ""you are a good girl."" What a good girl!

[lmtext] Throw Litter

Mary and her classmates went outing last weekend. Someone was flying kites, some people were having snacks. There were litters on the road. Mary picked up the waste bottles and paper the put them in the dustbin. The teacher praised Mary

for her good deed.

Last weekend, Mary went to the park with her classmates. They had a picnic in the park. Some people flew kites there. They had great fun there. Mary saw some rubbish on the road. She picked up the rubbish and threw it into the dustbin.

The teacher praised Mary.

Last Saturday, Mary's class went to the park. They brought some food and had a picnic on the grass. After that, they flew kites there. Suddenly, Mary found that there was some rubbish on the road. She then picked up the rubbish and threw it into the dustbin. Mary's teacher saw this. She said ""Well done"" to Mary. Mary was very happy.

Mary went to the park with her friend last weekend. They had a picnic there, while some people were flying kites. Mary's friend wanted to fly a kite too. So she threw waste bottles and paper on the ground and ran away. Mary saw this and picked up the rubbish. Then she threw it into the garbage can. A woman noticed what Mary had done. She praised Mary for her good behavior.

Mary went to the park to have a picnic with her friend last Sunday. They brought some juice and bread as lunch. After lunch, they joined other people to fly kites. Mary saw some waste bottles and paper on the ground. Someone threw them away after having a picnic. Mary cleaned the road, putting the garbage into a garbage can. A lady saw this and praised Mary for what she had done.

Last weekend, Mary and her classmates went to the park. Some of them flew kites, and some of them had food on the grass. Mary brought some juice, bread and biscuits to share with her friend. After they finished eating, her friend went

to fly a kite. Mary gathered their waste bottles and paper and was about to threw them into the dustbin. Suddenly, she saw some garbage on the ground. She

picked up the garbage, and threw it away with their waste bottles and paper. Her good behavior was noticed by the manager of the park. The manager praised her.

Last weekend, Mary went outing with her classmates. Mary and her friend were having drinks and some bread. Others were flying kites or playing games. After a while, there were litters on the ground. Mary saw these and started to pick up all the waste paper and bottles. She put them into the dustbin. Mary's teacher praised her for what she had done.

Mary went for an outing with her classmates last weekend. Some people played games and some people went to fly kites. Mary and Lily were having some snacks. When they were about to play, Mary noticed that there were litters around them. So she picked up the waste bottles and paper and threw them in the dustbin. Just then, her teacher saw it and praised Mary for what she did.

The school held an outing last weekend. Mary and her classmates had fun there. Some people were playing games while some were flying kites. Mary and one of her classmates were having some snacks. Then, Mary found that there were some waste paper and bottles on the ground. So she threw all of them into the dustbin. At last, the ground became clean and Mary was praised by her teacher.

Mary and her classmates went for an outing last weekend. They were very happy. Someone was flying kites, some were having food. After having lunch, they went on playing games. Mary noticed that there were some litters on the ground. So

she picked up all the litters and then put them in the dustbin. Mary's good deed was saw by her teacher. The teacher praised Mary and felt proud of what she had done.

Last Saturday, Mary's teacher took her class to an outing. The whole class were very happy then. Some people were flying kites while some were playing games. At lunch time, they had food and drank juice together. After that, there were some waste bottles and paper on the road. Mary started to pick them up and threw them into the dustbin. Her teacher saw it and spoke highly of what Mary had done.

Mary felt very proud of herself.

Last weekend Mary and her classmates went outing and had a picnic. Some people were flying kites, some people were having snacks. Suddenly, they found there was a lot of litter on the road. Mary picked up the waste bottles and paper the put them in the dustbin. The teacher praised Mary for her good behavior.

Last weekend Mary went to the park with Some friends. Some of them were flying kites. Some friends were eating food. Suddenly, they saw there was some rubbish on the road. Mary picked up the rubbish and put it into the garbage. The teacher said Mary was good.

English Oral Translation(oral_translation)

# Test paper example:

(1)Necessary node:[topic],use line breaks for separation. Refer to the [topic] restrictions on necessary node of story retelling question type for the standard description.

(2)Unnecessary nodes:[number_replace], [vocabulary] and [lmtext], refer to the restrictions on unnecessary nodes of sentence question type for the standard description.

[topic]

  1. British People

    1. British people usually say ""hello"" or ""nice to meet you"" and shake

your hand when they meet you for the first time. They behave politely in public. They think it's rude to push in before others. They always queue. They are very polite at home as well. When in Rome, do as the Romans do. When we are in a strange place, we should do as the local people do.

  1. For the first meeting, the English will usually say ""hello"" or ""nice to meet you"" and shake hands with you. In the public places, they behave

themselves well; they think that jumping in the line is a rude behavior, so they always line up. They are often very polite at home. When we are in a strange place, do in Rome as Rome does. We should behave well as local people.

  1. When they meet for the first time, the British usually say ""hello"" or ""nice to meet you"", and shake hands with each other. In public, they behave themselves appropriately. They think it is impolite to jump the queue, and they always wait in line patiently for their turns. They are also very polite at home. As the saying goes, ""when in Rome, do as the Romans do"". When we are in a strange place, we should act as the locals do.

    1. When first meet, English are likely to say ""hello"" or ""nice to meet

you"" and shake hands with you. They behave well in public. They usually line up because they think queue jumping is very impolite. And they are also very polite at home. There is an old saying ""Do in Rome as Rome does"". So when we are in a new place, we should behave ourselves as the locals do.

  1. When meeting for the first time, Englishmen usually say ""hello"" or ""nice to meet you"" with a handshake. They behave themselves well in public places.

They regard jumping a queue as one of the rude behavior, so they always queue up. They are also very polite at home. When in Rome, do as the Romans do. When we are in a strange place, we should behavior just like the local people.

  1. For the first meeting, English people usually say ""Hello"" or ""Nice to meet you"" and shake hands with you. In the public place, they also act very decently. In their views, it is very impolite to cut in line. They have formed a habit to wait in a queue. At home, they are also very polite. When in a strange place, we should do in Rome as the Romans do. Moreover, it is also polite that

    we behave like the local people.

    1. In first meeting, the English often say ""hi"" or ""nice to meet you!"" and then shake hands with you. In public occasions, they behave mannerly. They think jumping a queue is impolite and they always line up. Also, they are polite at home. When in Rome do as the Romans do. When we are in a strange land, we should behave like the natives.

      [lmtext] British People

      British people usually say ""hello"" or ""nice to meet you"" and shake your hand when they meet you for the first time. They behave politely in public. They

      think it's rude to push in before others. They always queue. They are very polite at home as well. When in Rome, do as the Romans do. When we are in a strange place, we should do as the local people do.

      For the first meeting, the English will usually say ""hello"" or ""nice to meet you"" and shake hands with you. In the public places, they behave themselves well; they think that jumping in the line is a rude behavior, so they always line up. They are often very polite at home. When we are in a strange place, do in Rome as Rome does. We should behave well as local people.

      When they meet for the first time, the British usually say ""hello"" or ""nice to meet you"", and shake hands with each other. In public, they behave themselves appropriately. They think it is impolite to jump the queue, and they always wait in line patiently for their turns. They are also very polite at home. As the saying goes, ""when in Rome, do as the Romans do"". When we are in a strange place, we should act as the locals do.

      When first meet, English are likely to say ""hello"" or ""nice to meet you"" and shake hands with you. They behave well in public. They usually line up because they think queue jumping is very impolite. And they are also very polite at

      home. There is an old saying ""Do in Rome as Rome does"". So when we are in a new place, we should behave ourselves as the locals do.

      When meeting for the first time, Englishmen usually say ""hello"" or ""nice to meet you"" with a handshake. They behave themselves well in public places. They regard jumping a queue as one of the rude behavior, so they always queue up.

      They are also very polite at home. When in Rome, do as the Romans do. When we are in a strange place, we should behavior just like the local people.

      For the first meeting, English people usually say ""Hello"" or ""Nice to meet you"" and shake hands with you. In the public place, they also act very

      decently. In their views, it is very impolite to cut in line. They have formed a habit to wait in a queue. At home, they are also very polite. When in a strange place, we should do in Rome as the Romans do. Moreover, it is also polite that

      we behave like the local people.

      In first meeting, the English often say ""hi"" or ""nice to meet you!"" and then shake hands with you. In public occasions, they behave mannerly. They think jumping a queue is impolite and they always line up. Also, they are polite at home. When in Rome do as the Romans do. When we are in a strange land, we should behave like the natives.

      [vocabulary]

      behavior /b ih 'hh ey v y ax/ uncourteous /,ah n 'k er t ir s/

Chinese Learning Engine xml Description

Question Type: ready_syllable

# ready_syllable level field description:
Attribute Note
phone_score Phone score
fluency_score Fluency score
tone_score Tone score
total_score Total score
beg_pse/end_pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

sentence level field description:

Attribute Note
time_len Time length(unit: frame,each frame is equivalent to 10ms)
beg_pos/end_pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
content Paper content

word level field description:

Attribute Note
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

syll level field description:

Attribute Note
beg pos / end pos Beginning/ending position(frame)
dp_message Missing-read/added-read message, 0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
rec_node_type Paper(paper content), si1(non-paper content)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

phone level field description:

Attribute Note
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
dp_message Missing-read/added-read message, 0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
content Paper content
rec_node_type Paper(paper content), si1(non-paper content)
perr_msg Error message:1(Phone error)2(Tone error)3(Phone and tone error)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

Question Type: read_word

# read_word level field description:
Attribute Note
phone_score Phone score
fluency_score Fluency score
tone_score Tone score
total_score Total score
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

sentence level field description:

Attribute Note
time_len Time length(unit: frame,each frame is equivalent to 10ms)
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
content Paper content

word level field description:

Attribute Note
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

syll level field description:

Attribute Note
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
dp_message Missing-read/added-read message,0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
rec_node_type Paper(paper content),si1(非paper content)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

phone level field description:

Attribute Note
beg pos / end pos Beginning/ending position(unit: frame,each frame is equivalent to 10ms)
dp_message Missing-read/added-read message,0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
content Paper content
rec_node_type Paper(paper content), si1(non-paper content)
perr_msg Error message:1(Phone error)2(Tone error)3(Phone and tone error)
time_len Time length(unit: frame,each frame is equivalent to 10ms

Question Type: read_sentence

read_sentence level field description:

Attribute Note
phone_score Phone score
fluency_score Fluency score
tone score Tone score
total score Total score
beg pos/end pos Beginning/ending position(unit,frame,each frame is equivalent to 10ms)
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

sentence level field description:

Attribute Note
phone_score Phone score
fluency_score Fluency score
tone_score Tone score
total_score Total score
beg_pos/end_pos Beginning/ending position(unit,frame,each frame is equivalent to 10ms)
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

word level field description:

Attribute Note
beg_pos/end_pos Beginning/ending position(frame)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

syll level field description:

Attribute Note
beg_pos / end_pos Beginning/ending position (frame)
dp_message Missing-read/added-read message, 0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
time_len Time length(unit: frame,each frame is equivalent to 10ms)
content Paper content
rec_node_type paper(paper content), si1(non-paper content)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

phone level field description:

Attribute Note
beg_pos / end_pos Beginning/ending position(frame)
dp_message Missing-read/added-read message,0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
content Paper content
rec_node_type Paper(paper content), si1(non-paper content)
content Paper content
perr_msg Error message:1(Phone error)2(Tone error)3(Phone and tone error)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

Question Type: read_chapter

read_chapter level field description:

Attribute Note
phone_score Phone score
fluency_score Fluency score
tone_score Tone score
total_score Total score
beg_pos / end_pos Beginning/ending position(frame)
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

sentence level field description:

Attribute Note
phone_score Phone score
fluency_score Fluency score
tone_score Tone score
total_score Total score
beg_pos / end_pos Beginning/ending position(frame)
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

word level field description:

Attribute Note
beg_pos / end_pos Beginning/ending position(frame)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
time_len Time length(unit: frame,each frame is equivalent to 10ms)

syll level field description:

Attribute Note
beg_pos / end_pos Beginning/ending position(frame)
dp_message Missing-read/added-read message, 0(Correct)16(Missing-read)32 (Added-read)64(Read back)128(Replaced)
symbol Pinyin: The number denotes the tone, and 5 denotes zeroth tone
content Paper content
rec_node_type Paper(paper content), si1(non-paper content)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

phone level field description:

Attribute Note
beg_pos / end_pos Beginning/ending position(frame)
dp_message Missing-read/added-read message,0(normal)16(reading missing)32(reading added)64(Read back)128(Replaced)
content Paper content
rec_node_type Paper(paper content), si1(non-paper content)
perr_msg Error message:1(Phone error)2(Tone error)3(Phone and tone error)
time_len Time length(unit: frame,each frame is equivalent to 10ms)

Learning Engine xml Output Table I

Question Type: read_word

# read_word level description
Attribute Note
beg_pos Multiple-word beginning boundary time
content Multiple-word content
end_pos Multiple-word ending boundary time
accuracy_socre Accuracy score
standard_score Standard score
except_info Exceptional information
is_rejected Rejected or not
total_score Average of total score of multiple words

sentence- level description

Attribute Note
beg_pos Multiple-word beginning boundary time
content Sentence content
end_pos Sentence ending boundary time
index Sentence index

Word-level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
end_pos Word ending boundary time
dp_message Word missing-read / added-read message
global_index Word index in the global chapter
index Word index in the sentence
property Word attribute(half-sentence| accent|key word etc.)
total_score Total score of words
pitch Word pitch information
pitch_beg Word pitch beginning value
pitch_end Word pitch ending value
werr_msg Word error message(no message is output for correct word)

syll(syllable) level description

Attribute Note
beg_pos Syllable beginning boundary time
content Syllable content
end_pos Syllable ending boundary time
serr_msg Syllable error message
syll_accent Syllable accent mark

phone(phoneme)level description

Attribute Note
beg_pos Phoneme beginning boundary time
content Phoneme content
end_pos Phoneme ending boundary time
dp_message Phoneme missing-read/added-read message

Question Type: read_ sentence

read_chapter(chapter)level description

Attribute Note
accuracy_score Accuracy score
beg_pos Chapter beginning time
content Chapter content
end_pos Chapter ending time
except_info Exceptional information
fluency_score Fluency score
integrity_score Integrity score
standard_score Standard score
is_rejected Rejected or not
total_score Total score of chapter
word_count Word count of chapter

sentence(sentence) level description

Attribute Note
beg_pos Sentence beginning boundary time
content Sentence content
end_pos Sentence ending boundary time
accuracy_score Accuracy score
fluency_score Fluency score
standard_score Standard score
index Sentence index
score(replaced with total_score) Total score, structure (hidden)
word_count Word count of sentence

word(word)level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
end_pos Word ending boundary time
dp_message Word missing-read / added-read message
global_index Word index in the global chapter
index Word index in the sentence
property Word attribute(half-sentence| accent|key word etc.)
total_score Total score of words
pitch Word pitch information
pitch_beg Word pitch beginning value
pitch_end Word pitch ending value
werr_msg Word error message(no message is output for correct word)

syll(syllable)- level description

Attribute Note
beg_pos Syllable beginning boundary time
content Syllable content
end_pos Syllable ending boundary time
serr_msg Syllable error message
syll_accent Syllable accent mark

phone(phoneme)

Attribute Note
beg_pos Phoneme beginning boundary time
content Phoneme content
end_pos Phoneme ending boundary time
dp_message Phoneme missing-read/added-read message

Question Type: read_chapter

read_chapter(chapter)level description

Attribute Note
accuracy_score Accuracy score
beg_pos Chapter beginning time
content Chapter content
end_pos Chapter ending time
except_info Exceptional information
fluency_score Fluency score
integrity_score Integrity score
standard_score Standard score
is_rejected Rejected or not
total_score Total score of chapter
word_count Word count of chapter

sentence(sentence)- level description

Attribute Note
beg_pos Sentence beginning boundary time
content Sentence content
end_pos Sentence ending boundary time
accuracy_score Accuracy score
fluency_score Fluency score
standard_score Standard score
index Sentence index
score(Replaced with total_score) Total score, structure (hidden)
word_count Word count of sentence

word(word)- level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
end_pos Word ending boundary time
dp_message Word missing-read / added-read message
global_index Word index in the global chapter
index Word index in the sentence
property Word attribute(half-sentence| accent|key word etc.)
total_score Total score of words
werr_msg Word error message(no message is output for correct word)

syll(syllable)- level description

Attribute Note
beg_pos Syllable beginning boundary time
content Syllable content
end_pos Syllable ending boundary time
serr_msg Syllable error message
syll_accent Syllable accent mark

phone(phoneme)level description

Attribute Note
beg_pos Phoneme beginning boundary time
content Phoneme content
end_pos Phoneme ending boundary time

Question Type: topic (story retelling)

# rec_paper- level description
Attribute Note
accuracy_score Semantic accuracy score
beg_pos Reading beginning time
content Reading identification content
end_pos Reading ending time
except_info Exceptional information
phone_score Pronouncing accuracy score
speeking_speed Speaking speed
total_score Total score

sentence- level description

Attribute Note
content Sentence content
index Sentence index

word level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
end_pos Word ending boundary time

Question Type: simple_expression(role play)

# rec_paper- level description
Attribute Note
beg_pos Reading beginning time
content Reading identification content
end_pos Reading ending time
except_info Exceptional information
phone_score Pronouncing accuracy score
total_score Total score

sentence- level description

Attribute Note
content Sentence content
index Sentence index

word- level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
end_pos Word ending boundary time

Question Type: choice

# free_choice- level description
Attribute Note
beg_pos Reading beginning time
content Reading identification content
end_pos Reading ending time
except_info Exceptional information
total_score Total score

Question Type: imitation(imitation reading)imitation_res(standard speech resource)

# read_chapter level description
Attribute Note
beg_pos Standard speech beginning time
content Standard speech content
end_pos Standard speech ending time

sentence- level description

Attribute Note
beg_pos Sentence beginning boundary time
content Sentence content
end_pos Sentence ending boundary time
index Sentence index

word- level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
dp_message Word missing-read / added-read message
end_pos Word ending boundary time
global_index Word index in the global chapter
index Word index in the sentence
pitch Word pitch information
pitch_beg Word pitch beginning value
pitch_end Word pitch ending value

Question Type: imitation(imitation reading)rec_paper

# read_chapter level description
Attribute Note
beg_pos Standard speech beginning time
cadence_score Cadence score
content Standard speech content
end_pos Standard speech ending time
except_info Exceptional information
is_rejected Rejected or not
rhythm_score Rhythm score
total_score Total score

sentence level description

Attribute Note
beg_pos Sentence beginning boundary time
content Sentence content
end_pos Sentence ending boundary time
index Sentence index

word- level description

Attribute Note
beg_pos Word beginning boundary time
content Word content
dp_message Word missing-read / added-read message
end_pos Word ending boundary time
global_index Word index in the global chapter
index Word index in the sentence
pitch Word pitch information
pitch_beg Word pitch beginning value
pitch_end Word pitch ending value
total_score Total score of words

Learning Engine xml Output Table II

Notes and Supplementary Description

Note Description
is_rejected returned field(part of evaluation question types have no this returned field ) true:rejected,indicating the engine has detected meaningless reading, and the value cannot be used as reference.
false:normal
Standard score in word, sentence and chapter question types Only when the number of words in the text>=5, there is a standard score.
Meaningless- talk detection function in word, sentence and chapter question types Only when the number of words in the text>=5, the meaningless talk detection function will be available. (This function is currently not available in the free-answer question type).
except_info attribute When except_info=28673,the hexadecimal value is 0x7001,indicating that the engine has judged that this speech is either of no-speech type or of small volume type. When except_info=28676,the hexadecimal value is 0x7004,indicating that the engine has judged that this speech is of meaningless talk type. When except_info=28680,the hexadecimal value is 0x7008,indicating that the engine has judged that this speech is of low SNR type. When except_info=28690,the hexadecimal value is 0x7012,indicating that the engine has judged that this speech is of clipping type.
dp_message attribute value When dp_message=0,it indicates that the engine has judged this word or phoneme is read normally. When dp_message=16, it indicates that the engine has judged this word or phoneme is missing in reading. When dp_message=32,it indicates that the engine has judged this word or phoneme is added in reading.
property, werr_msg attribute The werr_msg attribute only appears when the engine has judged that the word is read wrongly. For example, the property=16 of the word indicates word-connection is required at this word. If the werr_msg=512 attribute appears in xml, it indicates that the engine has judged that there is no word-connection in the speech at this word, otherwise it indicates that the engine has read it correctly. Word connection:property=16;werr_msg=512 Accent:property=32;rising and falling tone at the end of the sentence when werr_msg=2048:property=64; werr_msg=4096 Pause of meaning groups:property=2;werr_msg=256 Half-sentence:property=12,when the text word is followed by a single comma symbol,property is 12, this is the segmentation mark of the engine. This attribute will appear in the word before the sentence segmentation symbol-comma in the sentence, which is a mark of half sentence and has no special meaning.
serr_msg attribute When serr_msg=0,it indicates that the engine has judged this syllable is read correctly. When serr_msg=1,it indicates that the engine has judged this syllable is read wrongly. When serr_msg=2048,it indicates that accent is required for this syllable, but the engine has judged no accent is performed in the speech(at this time, syll_accent is 1). When serr_msg=2049,it indicates that accent is required for this syllable, but the engine has judge no accent is performed in the speech, and this syllable is read wrongly(at this time, syll_accent should be1)
syll_accent attribute When syll_accent=0,it indicates no accent is required for this syllable. When syll_accent=1, it indicates accent is required for this syllable.
Evaluation with Chinese characters superseded by Pinyin ,such as: jin1|tian1|天气 怎么样 (what is the weather like) The number of Chinese characters added in Pinyin should not exceed one third of the total number of Chinese characters in the test paper.

# Error Codes

Error Code Description
41895 The format of the test question is wrong. Please check whether the test text matches the test question, especially for English question types, special marks should be made in the test questions
10163 Parameter verification failed, which is caused by the client parameter verification failure, the client needs to change the request parameters according to the description in the returned message field
10313 The first frame of the request parameter failed to transmit app_id, or the transmitted app_id does not match API_key
40007 Audio decoding failed. Please check whether the transmitted audio corresponds to the encoding format described in the encoding field
11201 The usage of interface has exceeded the purchased maximum limit, please continue to use it after re-purchase
10114 Request is of timeout, the session time has exceeded 60s, please control the session time and keep it no more than 60s
10043 Audio decoding failed. Please ensure that the transmitted audio encoding format is consistent with the requested parameter
10161 Base64 decoding failed, check whether the sent data is base64 encoded
10200 Data reading is of timeout, check whether no data has been sent and the connection has not been closed for 10 seconds
10160 The request data format is illegal, check whether the request data is legal json
11200 Function is not authorized
60114 Evaluation audio length is too long
10139 Parameter error
48196 The instance prohibits repeated calls to this interface
40003 Not supported
40006 Invalid parameter
40007 Data size
40010 No response
40016 Initialization failed
40017 Not initialized
40023 Invalid configuration
40034 Parameter not set
40037 No evaluation text
40038 No evaluation speech
40040 Illegal data
42306 Insufficient authorization
68676 Talking meaningless

# Examples of Calls

# Pronunciation Assessment Stream API demo java Language (opens new window)

Q&A

How many concurrent channels does the Pronunciation Assessment Web API support?

# Answer: 50 channels are supported by default

What are the requirements for the audios supported by the Pronunciation Assessment?

Answer: If the audio sampling rate is 16k, the sampling accuracy is 16 bits, and mono audio. Refer to the audio provided in the demo for details of the sample audio.

What is the difference between the new streaming pronunciation assessment and the common pronunciation assessment (non-stream version)?

Answer:

The differences are as follows:

  1. The new streaming assessment version adopts a brand-new architecture, which is better than the common version in terms of assessment effect and service stability.
  1. It supports more question types such as the ones currently supported by English, including situational expression, text-reading reading, free talk, picture-talk, oral composition, etc. (these question types should be combined with the test paper customization service. Please check the introduction of corresponding packages on the product details page)
  1. Note:The new architecture only supports returning the results in xml format at present, json format will be supported in the near future.

# Contributing to the Documentation

Is something missing/incorrect? Please let us know by contacting openplatform@iflytek.com. If you know how to fix it straight away, don’t hesitate to create a request (opens new window) to help us improve our document.