语音事件检测
taskId
5df33c3c8c485b3a65b82f7b
taskId参数数据结构
| 参数名 | 类型 | 是否必有 | 说明 |
|---|---|---|---|
| speechs | Array | 是 | 识别的详细结果,具体数据结构如下 |
speechs参数数据结构
| 参数名 | 类型 | 是否必有 | 说明 |
|---|---|---|---|
| name | String | 是 | 上传的语音文件名称或者url |
| metadata | Object | 是 | 声音事件描述 |
| duration | Object | 否 | 表明事件在当前音频的时间段, key是每个待检测事件的编号，具体的事件名称保存在metadata的labels中 |
| prob | Object | 否 | 事件检测相对应事件msPerFrame概率值, key是每个待检测事件的编号，具体的事件名称保存在metadata的labels中 |
metadata参数数据结构
| 参数名 | 类型 | 是否必有 | 说明 |
|---|---|---|---|
| threshold | Number | 是 | 事件发生阈值,当检测事件的prob超过给定阈值时,才判定事件发生 |
| labels | Object | 是 | key是待检测事件的编号,value是具体的事件名称 |
| msPerFrame | Number | 是 | 表示一帧音频数据的时间长度,单位毫秒 |
| smoothing | Number | 是 | 表示事件应该维持的时间长度 |
返回示例
{
"5df33c3c8c485b3a65b82f7b": {
"speechs": [
{
"name": "15746978216180.7415171201913933.wav",
"metadata": {
"threshold": 0.7,
"labels": {
"0": "speech"
},
"msPerFrame": 80,
"smoothing": 0.32
},
"duration": {
"0": [
[
0.72,
5.28
],
[
6.24,
9
]
]
},
"prob": {
"0": [
0.0025766678154468536,
0.0000023800396320439177,
3.9011922581266845e-7,
4.3523516524146544e-7,
3.9934738538249803e-7,
1.995285998646068e-7,
7.351533781729813e-8,
1.5108078343928355e-7,
0.00033884341246448457,
0.9976348876953125,
0.9999402761459351,
0.9999699592590332,
0.9999772310256958,
0.9999845027923584,
0.9999840259552002,
0.9999785423278809,
0.9999737739562988,
0.9999823570251465,
0.9999896287918091,
0.9999905824661255,
0.9999916553497314,
0.9999945163726807,
0.9999955892562866,
0.9999957084655762,
0.9999927282333374,
0.9999842643737793,
0.9999605417251587,
0.999889612197876,
0.999723494052887,
0.9996234178543091,
0.9996151924133301,
0.9994339346885681,
0.9986730813980103,
0.9972832202911377,
0.9980137348175049,
0.9993705153465271,
0.9996931552886963,
0.9997128844261169,
0.9996844530105591,
0.999546468257904,
0.9990184307098389,
0.9984049201011658,
0.9993444085121155,
0.9998231530189514,
0.9998791217803955,
0.9998925924301147,
0.9999223947525024,
0.99993896484375,
0.9999387264251709,
0.9999294281005859,
0.9999111890792847,
0.9998918771743774,
0.9997963309288025,
0.9997418522834778,
0.9998685121536255,
0.9999250173568726,
0.9998955726623535,
0.9997171759605408,
0.9991645812988281,
0.9980161190032959,
0.9947212934494019,
0.9870010614395142,
0.9883460402488708,
0.993521511554718,
0.9941465854644775,
0.9611156582832336,
0.3832630515098572,
0.019315943121910095,
0.006675776559859514,
0.03219462186098099,
0.23181180655956268,
0.5803329944610596,
0.5652768015861511,
0.20836585760116577,
0.013594045303761959,
0.0018904516473412514,
0.01628764159977436,
0.620710015296936,
0.9466656446456909,
0.9950337409973145,
0.9995707869529724,
0.9998205304145813,
0.9996483325958252,
0.9992386102676392,
0.999570906162262,
0.9998517036437988,
0.9999555349349976,
0.9999607801437378,
0.9999452829360962,
0.9999552965164185,
0.9999699592590332,
0.9999740123748779,
0.9999748468399048,
0.9999663829803467,
0.9999498128890991,
0.9999624490737915,
0.9999713897705078,
0.9999663829803467,
0.9999525547027588,
0.9999566078186035,
0.9999750852584839,
0.9999874830245972,
0.999990701675415,
0.9999855756759644,
0.9999731779098511,
0.9999613761901855,
0.9999643564224243,
0.9999765157699585,
0.9999831914901733,
0.9999819993972778,
0.9999706745147705,
0.9999340772628784
]
}
}
]
},
"code": 0,
"message": "success",
"nonce": "0.3122552251458668",
"timestamp": 1576567341352
}