End-to-end time-domain multitask learning for ML-based speech enhancement
US11996114B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | May 15, 2021 |
| Grant date | May 28, 2024 |
| Priority date | — |
| Expiry date | Mar 20, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2021/02166
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Disclosed is a multi-task machine learning model such as a time-domain deep neural network (DNN) that jointly generate an enhanced target speech signal and target audio parameters from a mixed signal of target speech and interference signal. The DNN may encode the mixed signal, determine masks used to jointly estimate the target signal and the target audio parameters based on the encoded mixed signal, apply the mask to separate the target speech from the interference signal to jointly estimate the target signal and the target audio parameters, and decode the masked features to enhance the target speech signal and to estimate the target audio parameters. The target audio parameters may include a voice activity detection (VAD) flag of the target speech. The DNN may leverage multi-channel audio signal and multi-modal signals such as video signals of the target speaker to improve the robustness of the enhanced target speech signal.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.