发明名称 |
Speech recognition using multiple language models |
摘要 |
In accordance with one embodiment, a method of generating language models for speech recognition includes identifying a plurality of utterances in training data corresponding to speech, generating a frequency count of each utterance in the plurality of utterances, generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold, generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold, generating a grammar-based language model using the high-frequency plurality of utterances as training data, and generating a statistical language model using the low-frequency plurality of utterances as training data. |
申请公布号 |
US8972260(B2) |
申请公布日期 |
2015.03.03 |
申请号 |
US201213450861 |
申请日期 |
2012.04.19 |
申请人 |
Robert Bosch GmbH |
发明人 |
Weng Fuliang;Feng Zhe;Xu Kui;Zhao Lin |
分类号 |
G10L15/00;G10L15/32;G10L15/06;G10L15/18;G10L15/193;G10L15/197;G10L15/30 |
主分类号 |
G10L15/00 |
代理机构 |
Maginot Moore & Beck LLP |
代理人 |
Maginot Moore & Beck LLP |
主权项 |
1. A method of generating language models for speech recognition comprising:
identifying a plurality of utterances in training data corresponding to speech; generating a frequency count of each utterance in the plurality of utterances; generating a high-frequency plurality of utterances from the plurality of utterances having a frequency that exceeds a predetermined frequency threshold; generating a low-frequency plurality of utterances from the plurality of utterances having a frequency that is below the predetermined frequency threshold; generating with at least one processor a grammar-based language model using the high-frequency plurality of utterances as training data; storing the grammar based language model in a memory; generating with the at least one processor a statistical language model using the low-frequency plurality of utterances as training data; and storing the statistical language model in the memory. |
地址 |
Stuttgart DE US |