一、评估模式描述
·评测要求:支持30以内拼音。音频时长最长60秒。
·评测维度:支持返回单词精准度,单词流利度;支持音素精准度。
·评测功能:支持指定发音。
二、请求参数
主要请求参数说明:
| 参数名称 | 类型 | 描述 |
| ref_text | String | 被评估文本。使用 拼音 加上声调来表示。例如 shǎn,使用 shan3 来表示 shan(三声) |
| eval_mode | Integer | 评估模式。8:拼音评测模式 |
请求示例
三、返回结果
主要返回结果说明
| 参数名称 | 类型 | 描述 |
| SuggestedScore | Float | 建议评分 |
| PronAccuracy | Float | 整体精准度 |
| PronFluency | Float | 整体流利度 |
| Words.PronAccuracy | Float | 单词精准度 |
| Words.PronFluency | Float | 单词流利度 |
| Words.MatchTag | Integer | 当前词的音频与文本的匹配情况 |
| Words.PhoneInfos.PronAccuracy | Float | 音素精准度 |
| Words.PhoneInfos.MatchTag | Integer | 当前音素的音频与文本的匹配情况 |
返回示例
{ "code": 0, "message": "06104bab-98fa-4b4b-ab9e-f1800fcaebf4_5", "voice_id": "06104bab-98fa-4b4b-ab9e-f1800fcaebf4", "result": { "SuggestedScore": 75.57745361328125, "PronAccuracy": 75.57745361328125, "PronFluency": 0.9382091164588928, "PronCompletion": 1, "Words": [ { "MemBeginTime": 400, "MemEndTime": 870, "PronAccuracy": 75.57745361328125, "PronFluency": 0.9382091164588928, "ReferenceWord": "", "Word": "shan3", "MatchTag": 0, "KeywordTag": 0, "PhoneInfos": [ { "MemBeginTime": 400, "MemEndTime": 650, "PronAccuracy": 94.27549743652344, "DetectedStress": false, "Phone": "sh", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 }, { "MemBeginTime": 650, "MemEndTime": 870, "PronAccuracy": 66.22842407226562, "DetectedStress": false, "Phone": "an3", "ReferencePhone": "", "ReferenceLetter": "", "Stress": false, "MatchTag": 0 } ], "Tone": { "Valid": false, "RefTone": -1, "HypothesisTone": -1 } } ], "SentenceId": -1, "RefTextId": -1, "KeyWordHits": null, "UnKeyWordHits": null }, "final": 1}
四、指定发音
需要在声调检测下,使用 {::cmd{F_TDET=true}} 汉字 {::pron{p1,p2..},{p3,p4..}..} 指定发音,发音单元为 拼音。
五、请求参数
主要请求参数说明
| 参数名称 | 类型 | 描述 |
| ref_text | String | 被评估文本。使用| 划分多组分支 |
| eval_mode | Integer | 评估模式。8:拼音评测模式 |
请求示例
# 参数示例为websocket连接URL展开, 如:soe.cloud.tencent.com/soe/api/1306***?eval_mode=0&voice_format=1&…server_engine_type=16k_zheval_mode=8ref_text="{::cmd{F_TDET=true}}清平乐{::pron{yue4}}"score_coeff=1.000000voice_format=1
六、返回结果
主要返回结果说明
| 参数名称 | 类型 | 描述 |
| SentenceInfoSet.Words.PronAccuracy | Float | 单词精准度 |
| SentenceInfoSet.Words.PronFluency | Float | 单词流利度 |
| SentenceInfoSet.Words.MatchTag | Integer | 当前词的音频与文本的匹配情况 |
| SentenceInfoSet.Words.PhoneInfos.PronAccuracy | Float | 音素精准度 |
| SentenceInfoSet.Words.PhoneInfos.MatchTag | Integer | 当前音素的音频与文本的匹配情况 |
返回示例
{
"code": 0,
"message": "a560bdc1-9cca-4d0b-b470-91e7e3e7c27e_6",
"voice_id": "a560bdc1-9cca-4d0b-b470-91e7e3e7c27e",
"result": {
"SuggestedScore": 99.31161499023438,
"PronAccuracy": 99.31161499023438,
"PronFluency": 0.9807323813438416,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 280,
"MemEndTime": 590,
"PronAccuracy": 99.23593139648438,
"PronFluency": 0.9863236546516418,
"ReferenceWord": "qing1",
"Word": "清",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 280,
"MemEndTime": 470,
"PronAccuracy": 99.28839111328125,
"DetectedStress": false,
"Phone": "q",
"ReferencePhone": "q",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 470,
"MemEndTime": 590,
"PronAccuracy": 99.20970153808594,
"DetectedStress": false,
"Phone": "ing1",
"ReferencePhone": "ing1",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
},
{
"MemBeginTime": 590,
"MemEndTime": 780,
"PronAccuracy": 99.42112731933594,
"PronFluency": 1,
"ReferenceWord": "ping2",
"Word": "平",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 590,
"MemEndTime": 650,
"PronAccuracy": 99.52622985839844,
"DetectedStress": false,
"Phone": "p",
"ReferencePhone": "p",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 650,
"MemEndTime": 780,
"PronAccuracy": 99.36857604980469,
"DetectedStress": false,
"Phone": "ing2",
"ReferencePhone": "ing2",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
},
{
"MemBeginTime": 780,
"MemEndTime": 1190,
"PronAccuracy": 99.27776336669922,
"PronFluency": 0.9558734893798828,
"ReferenceWord": "yue4",
"Word": "乐",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 780,
"MemEndTime": 830,
"PronAccuracy": 99.16903686523438,
"DetectedStress": false,
"Phone": "y",
"ReferencePhone": "y",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 830,
"MemEndTime": 1190,
"PronAccuracy": 99.3321304321289,
"DetectedStress": false,
"Phone": "ve4",
"ReferencePhone": "ve4",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}