Method and apparatus for speech recognition adapted to an individual speaker
US5864810A · kind A · utility
136Cited by
9References
30Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jan 20, 1995 |
| Grant date | Jan 26, 1999 |
| Priority date | — |
| Expiry date | Jan 20, 2015 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and apparatus for automatic recognition of speech adapts to a particular speaker by using adaptation data to develop a transformation through which speaker independent models are transformed into speaker adapted models. The speaker adapted models are then used for speaker recognition and achieve better recognition accuracy than non-adapted models. In a further embodiment, the transformation-based adaptation technique is combined with a known Bayesian adaptation technique.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.