Word correction
This document describes how to integrate the English word correction speech evaluation feature.
Question type description
Scores each phoneme in an English word and provides feedback on mispronounced phonemes.
Evaluation request parameters
Field | Type | Optional | Description |
coreType | String | Required | en.mpd.score indicates English word correction. |
refText | String | Required | The reference text for scoring. |
rank | int | Optional | The scoring scale. This value can be set arbitrarily. The final score is recalculated as a proportion of 100. |
attachAudioUrl | int | Optional | Specifies whether to return the audio URL in the evaluation result. |
precision | double | Optional | Sets the scoring precision. Valid values are 0.1, 0.5, and 1. The default value is 1. If you set this parameter to a value other than 0.1 or 0.5, it is processed as 1. |
Parameter example
{
"coreType":"en.mpd.score",
"refText":"hot",
"rank":100,
"precision":1,
"attachAudioUrl":1
}Response result example
{
"tokenId": "6126571488bf5b0000090001",
"applicationId": "a148",
"audioUrl": "http:\/\/files.cloud.ssapi.cn:8080\/a148\/11ec05b2d06325249b36a148o261e7ba",
"connect": {
"param": {
"app": {
"timestamp": "1629902612",
"applicationId": "a148",
"sig": "c93d876e1038ae3c6cde0bfee24ca64570187188"
},
"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": "1629902612",
"userId": "ssound_text",
"sig": "c93d876e1038ae3c6cde0bfee24ca64570187188",
"connect_id": "6126571488bf5b00000b0002",
"clientId": "",
"applicationId": "a148"
},
"audio": {
"sampleBytes": 2,
"audioType": "ogg",
"sampleRate": 16000,
"channel": 1
},
"request": {
"request_id": "6126571488bf5b00000a0001",
"tokenId": "6126571488bf5b0000090001",
"precision": 1,
"attachAudioUrl": 1,
"refText": "hot",
"coreType": "en.mpd.score",
"rank": 100
}
},
"recordId": "11ec05b2d06325249b36a148o261e7ba",
"refText": "hot",
"dtLastResponse": "2021-08-25 22:43:32:490",
"cloud_platform": {
"origin_audio_length": 7807
},
"result": {
"accent": "am",
"wavetime": 1990,
"precision": 1,
"systime": 1814,
"rec": "hh aa t",
"version": "0.0.80.2021.7.24.00:01:28",
"rank": 100,
"info": {
"tipId": 10004,
"clip": 0,
"snr": 17.149954,
"volume": 77
},
"delaytime": 19,
"phone_str": "hh aa t",
"res": "eng.mpd.online.0.2",
"details": [
{
"char": "hh",
"type": 0
},
{
"char": "aa",
"type": 0
},
{
"char": "t",
"type": 0
}
],
"pretime": 34,
"overall": 100
},
"eof": 1
}Response result description
Key | Type | Description | Usage suggestion |
recordId | string | The unique ID of the audio file. | For reference |
tokenId | string | The unique ID of the user request. | For reference |
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 |
applicationId | string | The authorized account, which is the user's AppKey. | Internal parameter |
dtLastResponse | string | The timestamp of the cloud response. | Internal parameter |
eof | int | 0: The response is not complete. More results will follow. 1: All results for this evaluation have been returned. | Internal parameter |
refText | string | The input text for evaluation. | For reference |
params | object | Echoes the evaluation request parameters sent by the client. | |
- app | object | ||
- - applicationId | string | The authorized account, which is the provided evaluation AppKey. | |
- - userId | string | The user ID from your product. This can be a custom string. Use a unique ID for each user to make troubleshooting easier. | |
- - timestamp | string | The start time. | |
- - sig | string | The verification code. | |
- request | object | The node for scoring request parameters. | |
- audio | object | The node for audio parameters in the scoring request. | |
result | object | The evaluation result. | |
- version | string | The DPI engine version, including the release date. | Internal parameter |
- rank | int | The scoring scale. | Internal parameter |
- precision | float | The scoring precision. | Internal parameter |
- res | string | The name of the resource used for this evaluation. | Internal parameter |
- pretime | int | The time taken by the cloud to call the Start API. Unit: ms. | Internal parameter |
- systime | int | The total time taken for the entire evaluation process. Unit: ms. | Internal parameter |
- delaytime | int | The time from when the cloud finishes feeding the audio to when it gets the result. Unit: ms. | Internal parameter |
- wavetime | int | The duration of the audio. Unit: ms. | For reference |
- overall | float | The overall score. | Recommended field |
- rec | string | The recognition result. | Internal parameter |
-phone_str | string | The phonemes corresponding to the word. | Internal parameter |
- details | array | ||
- - char | string | The recognized phoneme. | For reference |
- - type | int | 0: Normal (the recognized phoneme matches the expected phoneme). 1: Insertion. 2: Deletion. 3: Substitution. | For reference |
Suggestions for displaying evaluation results
Dimension | Description | Details |
overall | Overall score | The overall evaluation score. |
Response on evaluation failure
If the result structure in the response is empty, the evaluation failed.
The response contains the `errId` and `error`. You can use the error code to determine the next steps for your application.
Error codes
For more information, see Evaluation error codes.