Targeted voice separation by speaker conditioned on spectrogram masking
US11922951B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 3, 2022 |
| Grant date | Mar 5, 2024 |
| Priority date | — |
| Expiry date | Jan 3, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L25/18
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques are disclosed that enable processing of audio data to generate one or more refined versions of audio data, where each of the refined versions of audio data isolate one or more utterances of a single respective human speaker. Various implementations generate a refined version of audio data that isolates utterance(s) of a single human speaker by processing a spectrogram representation of the audio data (generated by processing the audio data with a frequency transformation) using a mask generated by processing the spectrogram of the audio data and a speaker embedding for the single human speaker using a trained voice filter model. Output generated over the trained voice filter model is processed using an inverse of the frequency transformation to generate the refined audio data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.