Voice-based multimodal speaker authentication using adaptive training and applications thereof
US7529669B2 · kind B2 · utility
6Cited by
1References
8Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jun 13, 2007 |
| Grant date | May 5, 2009 |
| Priority date | — |
| Expiry date | Jun 13, 2027 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L17/10
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A voice based multimodal speaker authentication method and telecommunications application thereof employing a speaker adaptive method for training phenome specific Gaussian mixture models. Applied to telecommunications services, the method may advantageously be implemented in contemporary wireless terminals.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.