发明名称 |
Low latency real-time speech transcription |
摘要 |
Systems and methods for low-latency real-time speech recognition/transcription. A discriminative feature extraction, such as a heteroscedastic discriminant analysis transform, in combination with a maximum likelihood linear transform is applied during front-end processing of a digital speech signal. The extracted features reduce the word error rate. A discriminative acoustic model is applied by generating state-level lattices using Maximum Mutual Information Estimation. Recognition networks of language models are replaced by their closure. Latency is reduced by eliminating segmentation such that a number of words/sentences can be recognized as a single utterance. Latency is further reduced by performing front-end normalization in a causal fashion.
|
申请公布号 |
US7941317(B1) |
申请公布日期 |
2011.05.10 |
申请号 |
US20070758037 |
申请日期 |
2007.06.05 |
申请人 |
AT&T INTELLECTUAL PROPERTY II, L.P. |
发明人 |
GOFFIN VINCENT;RILEY MICHAEL DENNIS;SARACLAR MURAT |
分类号 |
G10L15/02;G10L15/04;G10L15/14 |
主分类号 |
G10L15/02 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|