发明名称 |
Minimum bayesian risk methods for automatic speech recognition |
摘要 |
A hypothesis space of a search graph may be determined. The hypothesis space may include n hypothesis-space transcriptions of an utterance, each selected from a search graph that includes t>n transcriptions of the utterance. An evidence space of the search graph may also be determined. The evidence space may include m evidence-space transcriptions of the utterance that are randomly selected from the search graph, where t>m. For each particular hypothesis-space transcription in the hypothesis space, an expected word error rate may be calculated by comparing the particular hypothesis-space transcription to each of the evidence-space transcriptions. Based on the expected word error rates, a lowest expected word error rate may be obtained, and the particular hypothesis-space transcription that is associated with the lowest expected word error rate may be provided. |
申请公布号 |
US9123333(B2) |
申请公布日期 |
2015.09.01 |
申请号 |
US201313771934 |
申请日期 |
2013.02.20 |
申请人 |
Google Inc. |
发明人 |
Amarilli Antoine;Mohri Mehryar;Allauzen Cyril |
分类号 |
G10L15/26;G10L15/04;G10L15/18;G10L15/06;G10L15/08 |
主分类号 |
G10L15/26 |
代理机构 |
McDonnell Boehnen Hulbert & Berghoff LLP |
代理人 |
McDonnell Boehnen Hulbert & Berghoff LLP |
主权项 |
1. A method comprising:
selecting, by a computing device, n hypothesis-space transcriptions of an utterance from a search graph that includes t>n transcriptions of the utterance, wherein selecting the n hypothesis-space transcriptions comprises determining n best transcriptions of the utterance according to a maximum a posteriori (MAP) technique; randomly selecting m evidence-space transcriptions of the utterance from the search graph, wherein t>m; for each particular hypothesis-space transcription of the n hypothesis-space transcriptions, calculating an expected word error rate by comparing the particular hypothesis-space transcription to the randomly selected m evidence-space transcriptions; based on the expected word error rates, determining a lowest expected word error rate; and providing the particular hypothesis-space transcription that is associated with the lowest expected word error rate. |
地址 |
Mountain View CA US |