发明名称 |
SYSTEMS AND METHODS FOR IMPROVING SPEECH RECOGNITION PERFORMANCE BY GENERATING COMBINED INTERPRETATIONS |
摘要 |
The systems and methods disclosed herein combine a plurality of interpretations of a voice-based input. The systems and methods may receive the voice-based input, process it using one or more automatic speech recognition modules to obtain a plurality of interpretations, and identify an entity set for each of the plurality of interpretations. The systems and methods may further generate a combined interpretation based on a first interpretation and second interpretation selected form the plurality of interpretations and assign a semantic score to the combined interpretation based on the entity sets of the first and second interpretation. |
申请公布号 |
US2016180840(A1) |
申请公布日期 |
2016.06.23 |
申请号 |
US201414578843 |
申请日期 |
2014.12.22 |
申请人 |
ROVI GUIDES, INC. |
发明人 |
Siddiq Abubakkar;Venkataraman Sashikumar |
分类号 |
G10L15/18;H04N21/482;H04N21/422 |
主分类号 |
G10L15/18 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for combining a plurality of interpretations of a voice-based input, the method comprising:
receiving, using control circuitry, the voice-based input; processing the voice-based input using one or more automatic speech recognition modules to obtain a plurality of interpretations of the voice-based input; identifying an entity set for each of the plurality of interpretations; generating a combined interpretation based on a first interpretation and a second interpretation, wherein both the first interpretation and the second interpretation are selected from the plurality of interpretations; and assigning a semantic score to the combined interpretation based on the entity set of the first interpretation and the entity set of the second interpretation. |
地址 |
Santa Clara CA US |