Online maximum-likelihood mean and variance normalization for speech recognition
US9280979B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Mar 6, 2015 |
| Grant date | Mar 8, 2016 |
| Priority date | — |
| Expiry date | Mar 6, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/34
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A feature transform for speech recognition is described. An input speech utterance is processed to produce a sequence of representative speech vectors. A time-synchronous speech recognition pass is performed using a decoding search to determine a recognition output corresponding to the speech input. The decoding search includes, for each speech vector after some first threshold number of speech vectors, estimating a feature transform based on the preceding speech vectors in the utterance and partial decoding results of the decoding search. The current speech vector is then adjusted based on the current feature transform, and the adjusted speech vector is used in a current frame of the decoding search.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.