发明名称 |
Providing pre-computed hotword models |
摘要 |
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, for each of multiple words or sub-words, audio data corresponding to multiple users speaking the word or sub-word; training, for each of the multiple words or sub-words, a pre-computed hotword model for the word or sub-word based on the audio data for the word or sub-word; receiving a candidate hotword from a computing device; identifying one or more pre-computed hotword models that correspond to the candidate hotword; and providing the identified, pre-computed hotword models to the computing device. |
申请公布号 |
US9263042(B1) |
申请公布日期 |
2016.02.16 |
申请号 |
US201414340833 |
申请日期 |
2014.07.25 |
申请人 |
Google Inc. |
发明人 |
Sharifi Matthew |
分类号 |
G10L15/26;G10L15/00;G10L25/00;G10L15/22;G10L15/06 |
主分类号 |
G10L15/26 |
代理机构 |
Fish & Richardson P.C. |
代理人 |
Fish & Richardson P.C. |
主权项 |
1. A computer-implemented method comprising:
obtaining, by a server for each of multiple words or sub-words, audio data corresponding to multiple users speaking the word or sub-word; training, by the server for each of the multiple words or sub-words, a hotword model for the word or sub-word based on the audio data for the word or sub-word, wherein the hotword model for the word or sub-word is a model that is used to detect an utterance of the word or sub-word in audio input data without transcribing the word or sub-word from input audio data; storing each of the trained hotword models as a pre-computed hotword model; receiving, by the server, a candidate hotword from a computing device; identifying, by the server, one or more of the stored pre-computed hotword models that correspond to the candidate hotword; and providing, by the server, the identified, one or more of the stored pre-computed hotword models to the computing device. |
地址 |
Mountain View CA US |