Apparatus and method for speech enhancement and feedback cancellation using a neural network
US12413916B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 9, 2023 |
| Grant date | Sep 9, 2025 |
| Priority date | — |
| Expiry date | Mar 8, 2044 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04R2225/43
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
A hearing device includes a deep/recurrent neural network trained to jointly perform sound enhancement and feedback cancellation. During training a neural network is connected between a simulated input and a simulated output of the hearing device. The neural network is operable to change a response affecting the simulated output. The neural network is trained by applying the simulated input to the deep neural network while applying the feedback path response between the simulated input and the simulated output. The deep-neural network is trained to reduce an error between the simulated output and the reference audio signal and used for sound enhancement in the device.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.