This document details the technical parameters and response for the Chinese single-character assessment. It supports scoring for polyphonic characters, initials, finals, and tones, and includes audio quality and confidence level analysis.-Smart Science and Education Content Platform(SSECP)-阿里云帮助中心

This document provides technical specifications for the read-aloud assessment of Chinese single characters, words, and idioms. It is intended for developers during product integration.

Description

Supports read-aloud assessment for characters, words, and idioms, including polyphonic characters.
Returns the overall score, the score for each character, the initial and final scores for each pinyin, the tone score, and the URL of the user's audio.

Assessment request parameters

Field	Type	Optional	Description
coreType	String	Required	cn.word.score indicates a Chinese single-character assessment.
refText	String	Required	Scoring reference: To count (shu3)
rank	int	Optional	The scoring scale. The final score is rescaled to a 100-point system. You can set this to any integer.
precision	double	Optional	Scoring precision. Valid values are 0.1, 0.5, and 1. The default is 1.
attachAudioUrl	int	Optional	Specifies whether to return the audio URL in the assessment result. 0: No. 1: Yes.
outputPhones	int	Optional	Specifies whether the output includes scores for the initials and finals of each character. The default value is 1.1: The returned initial and final characters require mapping to correspond to the actual phonemes.2: The actual initial and final information is returned.For example, if outputPhones is 1: {"chn_char":"you","char":"you","phn":0,"overall":0,"pron":0,"tone":3,"tonescore":0,"confidence":[0,0,0,0,0],"score":0,"dp_type":1,"start":0,"end":0,"dur":0,"fluency":0,"phone":[{"char":"ii","score":0},{"char":"iu","score":0}]}If outputPhones is 2: {"chn_char":"you","char":"you","phn":0,"overall":0,"pron":0,"tone":3,"tonescore":0,"confidence":[0,0,0,0,0],"score":0,"dp_type":1,"start":0,"end":0,"dur":0,"fluency":0,"phone":[{"char":"y","score":0},{"char":"ou","score":0}]}
symbol	int	Optional	If multiple consecutive punctuation marks precede a character, only the first is displayed. If multiple consecutive punctuation marks follow a character, only the three closest to the character are output. Valid values are 0 and 1. The default is 0, which disables this feature.
typeThres	int	Optional	Scoring strictness. A higher value has less impact on the score.1: Strict2: Loose3: Very Strict4: Very Loose0: Default (feature disabled)
use_cws	int	Optional	Enables the Chinese word segmentation (CWS) feature for better support of polyphonic characters and numbers. Valid values are 0 and 1. The default is 0, which disables this feature.

Parameter example

{
   "coreType": "en.word.score",
   "refText": "number",
   "rank": 100,
   "precision": 1,
   "outputPhones":1,
   "attachAudioUrl":1
}

Example response

{
    "tokenId": "6124bfae88bf5b0000010001", // The unique ID of the user request
    "applicationId": "a148",   // The authorized AppKey
    "dtLastResponse": "2021-08-24 17:45:20:300",
    "audioUrl": "http:\/\/files.cloud.ssapi.cn:8080\/a148\/11ec01828d53e9a1808aa148v2618ae7",    // The user's audio URL
    "connect": {   // Internal parameter node. You can ignore this.
        "param": {
            "app": {
                "timestamp": "1629798318",
                "applicationId": "a148",
                "sig": "bbce9709c2315ba2feddef73de75f4aa2f1b726a"
            },
            "sdk": {
                "os": "6.2(9200)1",
                "product": "",
                "source": 7,
                "protocol": 1,
                "os_version": "6.2(9200)",
                "arch": "586",
                "version": 16778752
            }
        },
        "cmd": "connect"
    },
    "params": {
        "app": {    // Internal parameter node. You can ignore this.
            "timestamp": "1629798318",
            "userId": "ssound_text",
            "sig": "bbce9709c2315ba2feddef73de75f4aa2f1b726a",
            "connect_id": "6124bfae88bf5b0000030002",
            "clientId": "",
            "applicationId": "a148"
        },
       "audio": {       // Audio parameter node
            "sampleBytes": 2,   // Bytes per sample. Supports 1 or 2 bytes.
            "audioType": "ogg", // Audio format type
            "sampleRate": 16000, // Sample rate
            "channel": 1       // Mono channel. The assessment only supports mono.
        },
        "request": {    // Scoring request. Parameters passed in by the client.
            "request_id": "6124bfae88bf5b0000020001",
            "tokenId": "6124bfae88bf5b0000010001",
            "rank": 100,
            "precision": 1,
            "coreType": "cn.word.score",  // Question type
             "refText": "shu(shu3)",     // Assessment text
           "rank": 100,
           "precision": 1,
           "outputPhones":1,
           "attachAudioUrl":1
        }
    },
    "recordId": "11ec04bffc5c410d8ceca148c2619a1a",
      "refText": "shu(shu3)",
    "result": {
        "overall": 67,    // Overall score
        "wavetime": 1990,    // Audio duration in ms
        "precision": 1,      // The scoring precision set in the assessment request. Only 0.1, 0.5, or 1 is supported. The default is 1. If the value is not 0.1 or 0.5, it is treated as 1.
        "forceout": 0,
        "phn": 85, // Pronunciation score without tone
        "res": "chn.wrd.online.1.0",  // The name of the resource used for the assessment
        "details": [  // Details for each character
            {
                "dp_type": 2, // 0: Normal pronunciation (usually not displayed). 1: The word was missed. 2: The word was repeated. 3: This character is not scored and serves as a comment.
                "pron": 67,  // Pronunciation score
                "dur": 300,  // Pronunciation duration of the character
                "chn_char": "shu",  // The assessed Chinese character
                "phn": 85,
                "confidence": [   // Confidence level. The values represent the probabilities of the character having a neutral, first, second, third, or fourth tone, respectively.
                    0,
                    3,
                    97,
                    0,
                    0
                ],
                "overall": 67,   // Overall score
                "tone": 3,  // The tone of a single pinyin, initial, or final. 0 to 4 correspond to neutral, first, second, third, and fourth tones.
                "char": "shu", // A single pinyin, initial, or final
                "score": 67,   
                "tonescore": 20,  // The tone score of the character
                "phone": [    // Detailed scoring information for initials and finals
                    {  
                        "char": "sh",  // Initial or final
                        "score": 93,   // Score for the initial or final
                        "end": 400,
                        "start": 260
                    },
                    {
                        "char": "u",
                        "score": 78,
                        "end": 410,
                        "start": 400
                    }
                ],
                "end": 820,
                "start": 520
            }
        ],
        "pretime": 6,
        "info": {
            "tipId": 0,
            "clip": 0,
            "snr": 31.557388,
            "volume": 84
        },
        "rank": 100,
        "delaytime": 49,
        "systime": 2528,
        "version": "0.0.80.2021.7.24.00:01:28",
        "tone": 20,
        "pron": 67
    },
    "eof": 1,
    "cloud_platform": {
        "origin_audio_length": 7807
    }
}

Response description

Key	Type	Description	Recommendations
recordId	string	The unique ID of the audio file.	For reference
tokenId	string	The unique ID of the user request.	For reference
applicationId	string	The authorized assessment account, which is the AppKey.	Internal parameter
dtLastResponse	string	The time when the cloud responded.	Internal parameter
audioUrl	string	The download URL for the user's audio. The audio is stored for about 20 days by default. For long-term storage, download it to your own server. The domain name varies by access region. The actual returned domain name prevails.
eof	int		Internal parameter
refText	string	The assessment text that was passed in.	For reference
params	object	Echoes the assessment request parameters passed in by the client.
- app	object
- - applicationId	string	The authorized assessment account, which is the AppKey.
- - userId	string	A custom string. We recommend setting a unique string for each user to help with troubleshooting.
- - timestamp	string	Start time.
- - sig	string	Verification code.
- request	object
- - coreType	string	The question type used.
- - tokenId	string	The unique ID of the user request.
- - refText	string	Reference text for scoring.
- audio	object
- - sampleRate	int	Sample rate.
- - channel	int	Sound channel.
- - sampleBytes	int	Bytes per sample. Supports 1 or 2 bytes.
- - audioType	string	Audio format.

result	object	Assessment result.
- version	string	The engine version, including the release date.	Internal parameter
- rank	int	Scoring scale.	Internal parameter
- res	string	The name of the resource used for this assessment type.	Internal parameter
- forceout	int		Internal parameter
- pretime	int	The time taken by the cloud to call the Start API, in ms.	Internal parameter
- delaytime	int	The time from when the cloud finishes feeding the audio to when it gets the result, in ms.	Internal parameter
- systime	int	The total time for the entire assessment process, in ms.
- wavetime	int	Audio duration, in ms.	For reference
- overall	float	Overall score.	Recommended field
- tone	float	Sentence intonation score (0-100).
- pron	float	Character pronunciation score.
- phn	float	Phoneme pronunciation score.
- precision	float	Scoring precision.
- details	array
- - pron	int	Pronunciation score with tone.	For reference
- - confidence	array	Confidence level.	The values represent the probabilities of the character having a neutral, first, second, third, or fourth tone, respectively.
- - dur	int	Indicates the end time of a word in the audio, in milliseconds (ms).
- - chn_char	string	Single character.
- - phn	int	Pronunciation score without tone.
- - overall	int	Overall score for the character.
- - tone	int	The tone corresponding to the character.	0 to 4 correspond to neutral, first, second, third, and fourth tones.
- - char	string	The pinyin corresponding to the character.
- - tonescore	int	The tone score of the character.
- - end	int	The duration of each word, in milliseconds (ms).
- - start	int	The start time of the character in the audio, in milliseconds (ms).
- - dp_type	int	Indicates insertions or omissions.	0: Normal pronunciation (usually not displayed). 1: The word was missed. 2: The word was repeated. 3: This character is not scored and serves as a comment.
- - phone	array	Detailed scoring information for initials and finals.
- - - char	string	Initial or final.	For reference
- - - score	int	Score for the initial or final.	For reference
- info	object
- - snr	float	Signal-to-noise ratio (SNR).	For reference
- - clip	float		Internal parameter
- - volume	int	Recording volume.	For reference
- - tipId	int	Audio quality.	Recommended field

Key response fields

Dimension	Description	Details
overall	Overall score for the character.	The overall score for the character.
pron	Pronunciation score.
details.score	Character score.	The score for a specific character. Check if it is empty before retrieving.
details.phn	Pronunciation score without tone.
details.phone.score	Initial and final score.	The score for the initials and finals corresponding to the character.

Response for a failed assessment

If the result structure in the response is empty, the assessment failed.
Retrieve the errId and error from the response. Use the error code to determine the next steps.

Error codes

For more information, see Assessment error codes.