System and method for speech separation and multi-talker speech recognition
US7664643B2 · kind B2 · utility
10Cited by
6References
18Claims
0Family size
Assignees
Inventors
Key dates
| Filing date | Aug 25, 2006 |
| Grant date | Feb 16, 2010 |
| Priority date | — |
| Expiry date | Apr 19, 2028 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2021/02166
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method, and a system to execute this method is being presented for the identification and separation of sources of an acoustic signal, which signal contains a mixture of multiple simultaneous component signals. The method represents the signal with multiple discrete state-variable sequences and combines acoustic and context level dynamics to achieve the source separation. The method identifies sources by discovering those frames of the signal whose features are dominated by single sources. The signal may be the simultaneous speech of multiple speakers.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.