一、评测模式描述
·评测要求:支持不超过30个汉字。音频时长最长60秒。
·评测维度:支持返回单词精准度,流利度,完整度;支持返回音素精准度。
·评测功能:支持实时评测;指定发音,声调检测。
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。不超过30个汉字。 |
| eval_mode | Integer | 评估模式。1:句子评测模式 |
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 |
| PronCompletion | Float | 整体完整度 |
| 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": "abf42150-3ed8-4b10-9ec6-971f79a4f6c3_1",
"voice_id": "abf42150-3ed8-4b10-9ec6-971f79a4f6c3",
"result": {
"SuggestedScore": 99.05166625976562,
"PronAccuracy": 99.05166625976562,
"PronFluency": 0.9839794039726257,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 310,
"MemEndTime": 580,
"PronAccuracy": 98.91350555419922,
"PronFluency": 0.9854655265808105,
"ReferenceWord": "",
"Word": "我",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 310,
"MemEndTime": 440,
"PronAccuracy": 98.6446533203125,
"DetectedStress": false,
"Phone": "w",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 440,
"MemEndTime": 580,
"PronAccuracy": 99.04792022705078,
"DetectedStress": false,
"Phone": "o3",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
},
{
"MemBeginTime": 580,
"MemEndTime": 730,
"PronAccuracy": 99.26715087890625,
"PronFluency": 0.9986396431922913,
"ReferenceWord": "",
"Word": "是",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 580,
"MemEndTime": 660,
"PronAccuracy": 99.28926849365234,
"DetectedStress": false,
"Phone": "sh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 660,
"MemEndTime": 730,
"PronAccuracy": 99.24503326416016,
"DetectedStress": false,
"Phone": "i4",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
},
{
"MemBeginTime": 730,
"MemEndTime": 1210,
"PronAccuracy": 99.04753875732422,
"PronFluency": 0.9678331017494202,
"ReferenceWord": "",
"Word": "谁",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 730,
"MemEndTime": 800,
"PronAccuracy": 99.19962310791016,
"DetectedStress": false,
"Phone": "sh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 800,
"MemEndTime": 1210,
"PronAccuracy": 98.9968490600586,
"DetectedStress": false,
"Phone": "ui2",
"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
使用汉字 {::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 |
| eval_mode | Integer | 评估模式。1:句子评测模式 |
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=1ref_text="我是谁{::pron{shei2}}"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 |
| 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.PhoneInfos.PronAccuracy | Float | 音素精准度 |
返回示例
{
"code": 0,
"message": "bc6ae589-9afd-401a-99a4-8a08d70b22de_1",
"voice_id": "bc6ae589-9afd-401a-99a4-8a08d70b22de",
"result": {
"SuggestedScore": 88.14450073242188,
"PronAccuracy": 88.14450073242188,
"PronFluency": 0.9721729159355164,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 250,
"MemEndTime": 580,
"PronAccuracy": 98.70932006835938,
"PronFluency": 0.9765400886535645,
"ReferenceWord": "",
"Word": "我",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 250,
"MemEndTime": 440,
"PronAccuracy": 98.03211975097656,
"DetectedStress": false,
"Phone": "w",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 440,
"MemEndTime": 580,
"PronAccuracy": 99.04792022705078,
"DetectedStress": false,
"Phone": "o3",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
},
{
"MemBeginTime": 580,
"MemEndTime": 740,
"PronAccuracy": 99.255859375,
"PronFluency": 0.9978697299957275,
"ReferenceWord": "",
"Word": "是",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 580,
"MemEndTime": 660,
"PronAccuracy": 99.28926849365234,
"DetectedStress": false,
"Phone": "sh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 660,
"MemEndTime": 740,
"PronAccuracy": 99.22245788574219,
"DetectedStress": false,
"Phone": "i4",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
},
{
"MemBeginTime": 740,
"MemEndTime": 1230,
"PronAccuracy": 70.172119140625,
"PronFluency": 0.9421089291572571,
"ReferenceWord": "",
"Word": "谁",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 740,
"MemEndTime": 810,
"PronAccuracy": 73.80574035644531,
"DetectedStress": false,
"Phone": "sh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 810,
"MemEndTime": 1230,
"PronAccuracy": 68.35530853271484,
"DetectedStress": false,
"Phone": "ei2",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}
七、声调检测
句子模式可以支持声调检测,使用 {::cmd{F_TDET=true}} + 汉字 的方式进行评测。
八、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 |
| eval_mode | Integer | 评估模式。1:句子评测模式 |
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=1ref_text="{::cmd{F_TDET=true}}我是谁"score_coeff=1.000000voice_format=1
九、返回结果
主要返回结果说明:
| 参数名称 | 类型 | 描述 |
| Words.Valid | Boolean | 检测结果是否有效注意:此字段可能返回 null,表示取不到有效值。 |
| Words.RefTone | Integer | 文本标准声调,数值范围[-1,1,2,3,4]注意:此字段可能返回 null,表示取不到有效值。 |
| Words.HypothesisTone | Integer | 实际发音声调,数值范围[-1,1,2,3,4]注意:此字段可能返回 null,表示取不到有效值。 |
返回示例
{
"code": 0,
"message": "aa915677-078c-434d-b2a9-9c6705e938bf_1",
"voice_id": "aa915677-078c-434d-b2a9-9c6705e938bf",
"result": {
"SuggestedScore": 98.98237609863281,
"PronAccuracy": 98.98237609863281,
"PronFluency": 0.9801464080810547,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 250,
"MemEndTime": 580,
"PronAccuracy": 98.70932006835938,
"PronFluency": 0.9765400886535645,
"ReferenceWord": "",
"Word": "我",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 250,
"MemEndTime": 440,
"PronAccuracy": 98.03211975097656,
"DetectedStress": false,
"Phone": "w",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 440,
"MemEndTime": 580,
"PronAccuracy": 99.04792022705078,
"DetectedStress": false,
"Phone": "o3",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": true,
"RefTone": 3,
"HypothesisTone": 3
}
},
{
"MemBeginTime": 580,
"MemEndTime": 730,
"PronAccuracy": 99.26715087890625,
"PronFluency": 0.9986396431922913,
"ReferenceWord": "",
"Word": "是",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 580,
"MemEndTime": 660,
"PronAccuracy": 99.28926849365234,
"DetectedStress": false,
"Phone": "sh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 660,
"MemEndTime": 730,
"PronAccuracy": 99.24503326416016,
"DetectedStress": false,
"Phone": "i4",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": true,
"RefTone": 4,
"HypothesisTone": 4
}
},
{
"MemBeginTime": 730,
"MemEndTime": 1230,
"PronAccuracy": 99.0447769165039,
"PronFluency": 0.9652596116065979,
"ReferenceWord": "",
"Word": "谁",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 730,
"MemEndTime": 800,
"PronAccuracy": 99.19962310791016,
"DetectedStress": false,
"Phone": "sh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 800,
"MemEndTime": 1230,
"PronAccuracy": 98.99315643310547,
"DetectedStress": false,
"Phone": "ui2",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": true,
"RefTone": 2,
"HypothesisTone": 2
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}