Method for performing stochastic matching for use in speaker verification
US5995927A · kind A · utility
Assignee
Inventor
Key dates
| Filing date | Mar 14, 1997 |
| Grant date | Nov 30, 1999 |
| Priority date | — |
| Expiry date | Mar 14, 2017 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L17/04
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method and an apparatus for performing stochastic matching of a set of input test speech data with a corresponding set of training speech data. In particular, a set of input test speech feature information, having been generated from an input test speech utterance, is transformed so that the stochastic characteristics thereof more closely match the stochastic characteristics of a corresponding set of training speech feature information. The corresponding set of training speech data may, for example, comprise training data which was generated from a speaker having the claimed identity of the speaker of the input test speech utterance. Specifically, in accordance with the present invention, a first covariance matrix representative of stochastic characteristics of input test speech feature information is generated based on the input test speech feature information. Then, a transformation is performed on the input test speech feature information, the transformation being based on the first covariance matrix and on a second covariance matrix representative of the stochastic characteristics of the training speech feature information. This transformation advantageously results in transf…
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.