This document describes the parameter settings, response results, and scoring mechanism for the English multiple-choice speech assessment feature. This feature applies to scenarios where users pronounce a fixed answer to obtain a precise score.-Smart Science and Education Content Platform(SSECP)-阿里云帮助中心

This document is a technical guide for developers who integrate the English multiple-choice speech assessment feature into their products.

Scenarios for this problem type:

A score is awarded only if the user pronounces the correct option completely and accurately.
The user pronounces one of the predefined answers, and a score is given based on the detected answer.

Assessment request parameters

Field	Type	Optional	Description
coreType	String	Required	en.choc.score indicates the English multiple-choice question type.
rank	int	Optional	The scoring scale. This value can be any number. The final score is rescaled to a 100-point system.
precision	double	Optional	The scoring precision. Supported values are 0.1, 0.5, and 1. The default is 1. If you set a value other than 0.1 or 0.5, the system uses 1.
lm	array	Required	An array of dictionaries that defines the multiple-choice options.1. In the lm sub-field, an answer value of 0 indicates an incorrect answer. A non-zero value indicates a correct answer. Note: The lm field is the lowercase form of LM.2. An overall score is awarded only if the correct text field is read with correct and complete pronunciation.
cmd_word	int	Optional	0: Uses the standard decoding network. This is the default.1: Uses a simplified decoding network. Decoding is faster, but performance may be lower. Set this parameter when the reference text is long.
attachAudioUrl	int	Optional	Specifies whether to return the audio URL in the assessment result. 0: Does not return the URL. 1: Returns the URL.

Parameter example

{
    "coreType": "en.choc.score",
    "rank": 2,
    "precision": 0.5,
    "attachAudioUrl":1,
    "lm": [
        {"answer": 0, "text": "In an office." },
        {"answer": 2, "text": "In a store." },
        {"answer": 0, "text": "In the street." }
    ]
}

Response example

{
    "tokenId": "61265ea188bf5b00000e0001",
    "applicationId": "a148",
    "audioUrl": "http:\/\/files.cloud.ssapi.cn:8080\/a148\/11ec05b74ec73b88a52ea1484261e844",
    "connect": {
        "param": {
            "app": {
                "timestamp": "1629904545",
                "applicationId": "a148",
                "sig": "234dac26e7e6ee712eae6cae644531047c27dfd3"
            },
            "sdk": {
                "os": "6.2(9200)1",
                "product": "",
                "source": 7,
                "protocol": 1,
                "os_version": "6.2(9200)",
                "arch": "586",
                "version": 16778752
            }
        },
        "cmd": "connect"
    },
    "params": {
        "app": {
            "timestamp": "1629904545",
            "userId": "ssound_text",
            "sig": "234dac26e7e6ee712eae6cae644531047c27dfd3",
            "connect_id": "61265ea188bf5b0000100002",
            "clientId": "",
            "applicationId": "a148"
        },
        "audio": {
            "sampleBytes": 2,
            "audioType": "ogg",
            "sampleRate": 16000,
            "channel": 1
        },
        "request": {
            "lm": [
                {
                    "text": "In an office.",
                    "answer": 0
                },
                {
                    "text": "In a store.",
                    "answer": 2
                },
                {
                    "text": "In the street.",
                    "answer": 0
                }
            ],
            "tokenId": "61265ea188bf5b00000e0001",
            "precision": 0.5,
            "attachAudioUrl": 1,
            "request_id": "61265ea188bf5b00000f0001",
            "rank": 2,
            "coreType": "en.choc.score"
        }
    },
    "recordId": "11ec05b74ec73b88a52ea1484261e844",
    "eof": 1,
    "result": {
        "overall": 0,
        "wavetime": 2990,
        "precision": 0.5,
        "systime": 3610,
        "res": "eng.choc.mfcc.0.1",
        "version": "0.0.80.2021.7.24.00:01:28",
        "info": {
            "tipId": 0,
            "clip": 0,
            "snr": 29.888056,
            "volume": 84
        },
        "rank": 2,
        "pretime": 3,
        "delaytime": 67
    },
    "dtLastResponse": "2021-08-25 23:15:43:906",
    "cloud_platform": {
        "origin_audio_length": 11600
    }
}

Response description

Key	Type	Description	Usage suggestion
recordId	string	The unique ID of the audio file.	For reference
tokenId	string	The unique ID of the request.	For reference
applicationId	string	The AppKey for the authorized account	Internal parameter
audioUrl	string	The URL of the user's audio. By default, the audio is stored in the cloud for one month. Save the audio to your product server.	For reference
dtLastResponse	string	The time of the cloud response.	Internal parameter
eof	int	0: The response is not complete. More results will follow.1: All results for this assessment have been returned.	Internal parameter
params	object	Echoes the assessment request parameters sent by the client.
- app	object
- - applicationId	string	AppKey of the authorization account
- - userId	string	The user ID. This is a custom string that helps you locate and troubleshoot issues.
- - timestamp	string	The start time.
- - sig	string	The verification code.
- - clientId	string
- request	object	The node for assessment request parameters.
- audio	object	The node for the audio parameters of the assessment request.
result	object	The assessment result.
- res	string	The name of the resource used to assess this question type.	Internal parameter
- version	string	The version and publish time of the DPI engine.	Internal parameter
- rank	int	The scoring scale.	Internal parameter
- precision	float	The scoring precision.	Internal parameter
- pretime	int	The time, in ms, that the cloud takes to call the Start API.	Internal parameter
- systime	int	The total time, in ms, for the entire assessment process.	Internal parameter
- delaytime	int	The time, in ms, from when the cloud finishes feeding the audio to when the result is obtained.	Internal parameter
- wavetime	int	The audio duration in ms.	For reference
- overall	float	The overall score.	Recommended field
- fake_words	object		(This field appears only when the assessment text contains invalid words. Each word is a node.)
- - char	string	A word that is not in the dictionary.
- info	object
- - snr	float	The signal-to-noise ratio. A higher value indicates clearer audio. Range: 0 to 40 dB. If this parameter affects the score, a corresponding tipId value is set.	For reference
- - clip	float	The audio volume is too high, which causes clipping. Range: 0 to 1. If this parameter affects the score, a corresponding tipId value is set.	Internal parameter
- - volume	int	The recording volume. Range: 0 to 180 dB.	For reference
- - tipId	int	The audio quality. For more information, see tipId prompt information.	Recommended field

Suggestions for displaying assessment results

Dimension	Description	Details
overall	Overall pronunciation score	An overall evaluation of the pronunciation of the selected sentence.

Response when assessment fails

An empty result structure in the response indicates that the assessment failed.
Retrieve the errId and error from the response. Your application can use the error code for further processing.

Error codes

For more information, see Assessment error codes.