一、评测模式描述
·评测要求:支持单词,组合词评测。音频时长最长60秒。
·评测维度:支持返回单词精准度,流利度;支持返回音素精准度。
·评测功能:支持重音检测,原始单词,音素到字母映射,音素到国际音标转换,指定发音,指定国际音标。
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。支持单词,组合词,缩写 |
| eval_mode | Integer | 评估模式。0:单词评测模式 |
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.PhoneInfos.PronAccuracy | Float | 音素精准度 |
| Words.PhoneInfos.Stress | Boolean | 当前评估文本对应音素是否为重音 |
| Words.PhoneInfos.DetectedStress | Boolean | 当前音频数据对应音素是否为重音 |
返回示例
{
"code": 0,
"message": "af31ab3f-9a5e-4a90-b17f-a5869b7c326a_1",
"voice_id": "af31ab3f-9a5e-4a90-b17f-a5869b7c326a",
"result": {
"SuggestedScore": 98.04969787597656,
"PronAccuracy": 98.04969787597656,
"PronFluency": 0.8466556668281555,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 390,
"MemEndTime": 1370,
"PronAccuracy": 98.04969787597656,
"PronFluency": 0.8466556668281555,
"ReferenceWord": "father_0",
"Word": "father",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 390,
"MemEndTime": 550,
"PronAccuracy": 96.76220703125,
"DetectedStress": false,
"Phone": "f",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 550,
"MemEndTime": 810,
"PronAccuracy": 97.25521850585938,
"DetectedStress": false,
"Phone": "aa",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 810,
"MemEndTime": 930,
"PronAccuracy": 99.20626068115234,
"DetectedStress": false,
"Phone": "dh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 930,
"MemEndTime": 1370,
"PronAccuracy": 98.97508239746094,
"DetectedStress": false,
"Phone": "er",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}
四、原始单词
数字类型使用英文评测会转换为对应英文单词,可在对应返回字段获取原始数字以及单词下标。
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。0:单词评测模式 |
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_eneval_mode=0rec_mode=0ref_text="1"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1
六、返回结果
主要返回结果说明:
| 参数名称 | 类型 | 描述 |
| Words.Word | String | 当前词 |
| Words.ReferenceWord | String | 原始单词 |
返回示例
{
"code": 0,
"message": "d91a2d4e-73c0-492f-89d1-115059453d87_1",
"voice_id": "d91a2d4e-73c0-492f-89d1-115059453d87",
"result": {
"SuggestedScore": 97.94207763671875,
"PronAccuracy": 97.94207763671875,
"PronFluency": 0.9294439554214478,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 210,
"MemEndTime": 690,
"PronAccuracy": 97.94207763671875,
"PronFluency": 0.9294439554214478,
"ReferenceWord": "1_0",
"Word": "one",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 210,
"MemEndTime": 290,
"PronAccuracy": 97.15730285644531,
"DetectedStress": false,
"Phone": "hh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 290,
"MemEndTime": 390,
"PronAccuracy": 97.685546875,
"DetectedStress": false,
"Phone": "w",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 390,
"MemEndTime": 550,
"PronAccuracy": 98.44290924072266,
"DetectedStress": false,
"Phone": "ah",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 550,
"MemEndTime": 690,
"PronAccuracy": 98.48255920410156,
"DetectedStress": false,
"Phone": "n",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}
七、音素到字母映射
通过该功能,可以对音素映射字母进行标记。音素到字母映射结构:{::cmd{F_P2L=true}} + 评估文本。
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。0:单词评测模式 |
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_eneval_mode=0rec_mode=0ref_text="{::cmd{F_P2L=true}} happy"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1
九、返回结果
主要返回结果说明:
| 参数名称 | 类型 | 描述 |
| Words.Word | String | 当前单词 |
| Words.PhoneInfos.Phone | String | 当前单词的音素 |
| Words.PhoneInfos.ReferenceLetter | String | 当前单词的音素映射的字母 |
返回示例
{
"code": 0,
"message": "4984a513-e57f-4345-a926-df0298fd3a04_1",
"voice_id": "4984a513-e57f-4345-a926-df0298fd3a04",
"result": {
"SuggestedScore": 94.5397720336914,
"PronAccuracy": 94.5397720336914,
"PronFluency": 0.9604969024658203,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 200,
"MemEndTime": 650,
"PronAccuracy": 94.5397720336914,
"PronFluency": 0.9604969024658203,
"ReferenceWord": "happy_0",
"Word": "happy",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 200,
"MemEndTime": 260,
"PronAccuracy": 82.32677459716797,
"DetectedStress": false,
"Phone": "hh",
"ReferencePhone": "",
"ReferenceLetter": "h_0",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 260,
"MemEndTime": 340,
"PronAccuracy": 97.87178039550781,
"DetectedStress": false,
"Phone": "ae",
"ReferencePhone": "",
"ReferenceLetter": "a_1",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 340,
"MemEndTime": 420,
"PronAccuracy": 99.12616729736328,
"DetectedStress": false,
"Phone": "p",
"ReferencePhone": "",
"ReferenceLetter": "pp_2",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 420,
"MemEndTime": 650,
"PronAccuracy": 98.83436584472656,
"DetectedStress": false,
"Phone": "iy",
"ReferencePhone": "",
"ReferenceLetter": "y_4",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}
十、音素到国际音标转换
返回音素默认为智聆音素,使用 {::cmd{F_IPA=true}} + 单词 开启音素到国际⾳标转换功能。
十一、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。0:单词评测模式 |
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_eneval_mode=0rec_mode=0ref_text="{::cmd{F_IPA=true}} happy"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1
十二、返回结果
返回结果说明:
| 参数名称 | 类型 | 描述 |
| Words.PhoneInfos.Phone | String | 当前音节 |
返回示例
{
"code": 0,
"message": "3b651764-c4b4-4786-a8df-5f993aee34a8_1",
"voice_id": "3b651764-c4b4-4786-a8df-5f993aee34a8",
"result": {
"SuggestedScore": 94.5397720336914,
"PronAccuracy": 94.5397720336914,
"PronFluency": 0.9604969024658203,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 200,
"MemEndTime": 650,
"PronAccuracy": 94.5397720336914,
"PronFluency": 0.9604969024658203,
"ReferenceWord": "happy_0",
"Word": "happy",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 200,
"MemEndTime": 260,
"PronAccuracy": 82.32677459716797,
"DetectedStress": false,
"Phone": "'h",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 260,
"MemEndTime": 340,
"PronAccuracy": 97.87178039550781,
"DetectedStress": false,
"Phone": "æ",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 340,
"MemEndTime": 420,
"PronAccuracy": 99.12616729736328,
"DetectedStress": false,
"Phone": "p",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 420,
"MemEndTime": 650,
"PronAccuracy": 98.83436584472656,
"DetectedStress": false,
"Phone": "i",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}
十三、指定发音
使用 单词{::pron{p1,p2..},{p3,p4..}..} 指定发音,需要将国际音标通过音素映射表转换为智聆音素,参考音素映射表 — 智聆音素。
十四、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。0:单词评测模式 |
请求示例
音标单词多音词# 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_eneval_mode=0rec_mode=0ref_text="au{::pron{aw}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1server_engine_type=16k_eneval_mode=0rec_mode=0ref_text="happy{::pron{hh,ae,p,iy}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1server_engine_type=16k_eneval_mode=0rec_mode=0ref_text="use{::pron{y,uw,z},{y,uw,s}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1
十五、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": "9339be72-4799-4bbb-8e6d-e8148f45f2d9_1",
"voice_id": "9339be72-4799-4bbb-8e6d-e8148f45f2d9",
"result": {
"SuggestedScore": 94.50332641601562,
"PronAccuracy": 94.50332641601562,
"PronFluency": 0.9472841620445251,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 130,
"MemEndTime": 650,
"PronAccuracy": 94.50332641601562,
"PronFluency": 0.9472841620445251,
"ReferenceWord": "happy_0",
"Word": "happy",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 130,
"MemEndTime": 260,
"PronAccuracy": 82.18097686767578,
"DetectedStress": false,
"Phone": "hh",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 260,
"MemEndTime": 340,
"PronAccuracy": 97.87178039550781,
"DetectedStress": false,
"Phone": "ae",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 340,
"MemEndTime": 420,
"PronAccuracy": 99.12616729736328,
"DetectedStress": false,
"Phone": "p",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 420,
"MemEndTime": 650,
"PronAccuracy": 98.83436584472656,
"DetectedStress": false,
"Phone": "iy",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}
十六、指定国际音标
使用 单词{::ipapron{p1,p2..},{p3,p4..}..} 指定国际音标参考,音素映射表 — 国际音标。指定国际音标并不会返回结果,如需返回国际音标需要添加音素到国际音标转换。
十七、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。0:单词评测模式 |
请求示例
音标单词多音词国际音标指定+转换# 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_eneval_mode=0rec_mode=0ref_text="au{::ipapron{aʊ}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1voice_id=6bd18918-8d15-4272-b693-6c588f058a33server_engine_type=16k_eneval_mode=0rec_mode=0ref_text="happy{::ipapron{'h,æ,p,i}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1voice_id=6bd18918-8d15-4272-b693-6c588f058a33server_engine_type=16k_eneval_mode=0rec_mode=0ref_text="use{::ipapron{j,u,z},{j,u,s}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1voice_id=6bd18918-8d15-4272-b693-6c588f058a33server_engine_type=16k_eneval_mode=0rec_mode=0ref_text="{::cmd{F_IPA=true}}happy{::ipapron{'h,æ,p,i}}"score_coeff=1.000000sentence_info_enabled=0text_mode=0voice_format=1voice_id=6bd18918-8d15-4272-b693-6c588f058a33
十八、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": "70e2b951-fd1c-4b9a-b66f-935150e24da2_1",
"voice_id": "70e2b951-fd1c-4b9a-b66f-935150e24da2",
"result": {
"SuggestedScore": 94.50332641601562,
"PronAccuracy": 94.50332641601562,
"PronFluency": 0.9472841620445251,
"PronCompletion": 1,
"Words": [
{
"MemBeginTime": 130,
"MemEndTime": 650,
"PronAccuracy": 94.50332641601562,
"PronFluency": 0.9472841620445251,
"ReferenceWord": "happy_0",
"Word": "happy",
"MatchTag": 0,
"KeywordTag": 0,
"PhoneInfos": [
{
"MemBeginTime": 130,
"MemEndTime": 260,
"PronAccuracy": 82.18097686767578,
"DetectedStress": false,
"Phone": "'h",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 260,
"MemEndTime": 340,
"PronAccuracy": 97.87178039550781,
"DetectedStress": false,
"Phone": "æ",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 340,
"MemEndTime": 420,
"PronAccuracy": 99.12616729736328,
"DetectedStress": false,
"Phone": "p",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
},
{
"MemBeginTime": 420,
"MemEndTime": 650,
"PronAccuracy": 98.83436584472656,
"DetectedStress": false,
"Phone": "i",
"ReferencePhone": "",
"ReferenceLetter": "",
"Stress": false,
"MatchTag": 0
}
],
"Tone": {
"Valid": false,
"RefTone": -1,
"HypothesisTone": -1
}
}
],
"SentenceId": -1,
"RefTextId": -1,
"KeyWordHits": null,
"UnKeyWordHits": null
},
"final": 1
}