Alteration of speech within an audio stream based on a characteristic of the speech
US12067968B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 30, 2021 |
| Grant date | Aug 20, 2024 |
| Priority date | — |
| Expiry date | Mar 4, 2042 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04M2203/255
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
In some implementations, a system may receive an audio stream associated with a call between a user and an agent. The system may process, by the device and using a speech alteration model, speech from a first channel of the audio stream to alter the speech from having a first speech characteristic to having a second speech characteristic, wherein the speech alteration model is trained based on reference audio data associated with the first speech characteristic and the second speech characteristic and based on reference speech data associated with the first speech characteristic and the second speech characteristic. The system may extract the speech from the first channel that has the first speech characteristic. The system may provide, within a second channel of the audio stream, altered speech that corresponds to the speech and that has the first speech characteristic.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.