Semi-supervised training scheme for speech recognition
US12315499B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 14, 2022 |
| Grant date | May 27, 2025 |
| Priority date | — |
| Expiry date | Dec 14, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L15/02
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving a sequence of acoustic frames extracted from unlabeled audio samples that correspond to spoken utterances not paired with any corresponding transcriptions. The method also includes generating, using a supervised audio encoder, a target higher order feature representation for a corresponding acoustic frame. The method also includes augmenting the sequence of acoustic frames and generating, as output form an unsupervised audio encoder, a predicted higher order feature representation for a corresponding augmented acoustic frame in the sequence of augmented acoustic frames. The method also includes determining an unsupervised loss term based on the target higher order feature representation and the predicted higher order feature representation and updating parameters of the speech recognition model based on the unsupervised loss term.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.