Multi-pass speech activity detection strategy to improve automatic speech recognition
US9959887B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 8, 2016 |
| Grant date | May 1, 2018 |
| Priority date | — |
| Expiry date | Apr 26, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/225
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An automatic speech recognition system and a method performed by an automatic speech recognition system are provided. The method includes performing at least two passes of speech activity detection on an acoustic utterance uttered by a speaker. The at least two passes include an initial pass and a subsequent pass. The method further includes estimating at least one of feature statistics and transforms for acoustic feature extraction and acoustic modeling based on an output of an initial pass. The method further includes performing automatic speech recognition using an output of the subsequent pass while bypassing an output of the initial pass to recognize the acoustic utterance.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.