Adaptive decision directed speech recognition bias equalization method and apparatus
US5812972A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Dec 30, 1994 |
| Grant date | Sep 22, 1998 |
| Priority date | — |
| Expiry date | Dec 30, 2014 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0635
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present invention provides a speech recognizer that creates and updates the equalization vector as input speech is provided to the recognizer. The present invention includes a speech analyzer which transforms an input speech signal into a series of feature vectors or observation sequence. Each feature vector is then provided to a speech recognizer which modifies the feature vector by subtracting a previously determined equalization vector therefrom. The recognizer then performs segmentation and matches the modified feature vector to a stored model vector which is defined as the segmentation vector. The recognizer then, from time to time, determines a new equalization vector, the new equalization vector being defined based on the difference between one or more input feature vectors and their respective segmentation vectors. The new equalization vector may then be used either for performing another segmentation iteration on the same observation sequence or for performing segmentation on subsequent feature vectors.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.