Deep multi-channel acoustic modeling
US10726830B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 27, 2018 |
| Grant date | Jul 28, 2020 |
| Priority date | — |
| Expiry date | Jan 24, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2021/02166
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques for speech processing using a deep neural network (DNN) based acoustic model front-end are described. A new modeling approach directly models multi-channel audio data received from a microphone array using a first model (e.g., multi-channel DNN) that takes in raw signals and produces a first feature vector that may be used similarly to beamformed features generated by an acoustic beamformer. A second model (e.g., feature extraction DNN) processes the first feature vector and transforms it to a second feature vector having a lower dimensional representation. A third model (e.g., classification DNN) processes the second feature vector to perform acoustic unit classification and generate text data. These three models may be jointly optimized for speech processing (as opposed to individually optimized for signal enhancement), enabling improved performance despite a reduction in microphones and a reduction in bandwidth consumption during real-time processing.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.