Efficient dereverberation in networked audio systems
US9390723B1 · kind B1 · utility
4Cited by
0References
21Claims
0Family size
Inventors
Key dates
| Filing date | Dec 11, 2014 |
| Grant date | Jul 12, 2016 |
| Priority date | — |
| Expiry date | Jan 12, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2021/02082
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Features are disclosed for performing efficient dereverberation of speech signals captured with single- and multi-channel sensors in networked audio systems. Such features could be used in applications requiring automatic recognition of speech captured with sensors. Dereverberation is performed in the sub-band domain, and hence provides improved dereverberation performance in terms of signal quality, algorithmic delay, computational efficiency, and speed of convergence.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.