发明名称 |
LANGUAGE MODEL SPEECH ENDPOINTING |
摘要 |
An automatic speech recognition (ASR) system detects an endpoint of an utterance using the active hypotheses under consideration by a decoder. The ASR system calculates the amount of non-speech detected by a plurality of hypotheses and weights the non-speech duration by the probability of each hypotheses. When the aggregate weighted non-speech exceeds a threshold, an endpoint may be declared. |
申请公布号 |
WO2017003903(A1) |
申请公布日期 |
2017.01.05 |
申请号 |
WO2016US39491 |
申请日期 |
2016.06.27 |
申请人 |
AMAZON TECHNOLOGIES, INC. |
发明人 |
HOFFMEISTER, Bjorn;RASTROW, Ariya;LIU, Baiyang |
分类号 |
G10L25/87;G10L15/183;G10L25/78 |
主分类号 |
G10L25/87 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|