Directed audio for speech recognition
US9076450B1 · kind B1 · utility
256Cited by
7References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 21, 2012 |
| Grant date | Jul 7, 2015 |
| Priority date | — |
| Expiry date | Jan 3, 2033 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04R2430/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques are described for selecting audio from locations that are most likely to be sources of spoken commands or words. Directional audio signals are generated to emphasize sounds from different regions of an environment. The directional audio signals are processed by an automated speech recognizer to generate recognition confidence values corresponding to each of the different regions, and the region resulting in the highest recognition confidence value is selected as the region most likely to contain a user who is speaking commands.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.