Video-based sound source separation
US10078785B2 · kind B2 · utility
0Cited by
3References
19Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Dec 15, 2015 |
| Grant date | Sep 18, 2018 |
| Priority date | — |
| Expiry date | Apr 26, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L21/028
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A sound source separation method comprising the steps of determining at least one location of at least one sound source based on video data, determining initial estimates of at least two parameters characterizing an audio signal emitted by said sound source, said initial estimates being determined based on said at least one location, performing an expectation-maximization method for determining final estimates of said parameters, and separating the audio signal from a combination of audio signals based on said final estimates of said parameters.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.