Unsupervised HMM adaptation based on speech-silence discrimination
US6076057A · kind A · utility
51Cited by
16References
12Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | May 21, 1997 |
| Grant date | Jun 13, 2000 |
| Priority date | — |
| Expiry date | May 21, 2017 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/142
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An unsupervised, discriminative, sentence level, HMM adaptation based on speech-silence classification is presented. Silence and speech regions are determined either using a speech end-pointer or the segmentation obtained from the recognizer in a first pass. The discriminative training procedure using a GPD or any other discriminative training algorithm, employed in conjunction with the HMM-based recognizer, is then used to increase the discrimination between silence and speech.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.