Joint unsupervised and supervised training for multilingual ASR
US12249317B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 6, 2022 |
| Grant date | Mar 11, 2025 |
| Priority date | — |
| Expiry date | Jul 16, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/048
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method includes receiving audio features and generating a latent speech representation based on the audio features. The method also includes generating a target quantized vector token and a target token index for a corresponding latent speech representation. The method also includes generating a contrastive context vector for a corresponding unmasked or masked latent speech representation and deriving a contrastive self-supervised loss based on the corresponding contrastive context vector and the corresponding target quantized vector token. The method also include generating a high-level context vector based on the contrastive context vector and, for each high-level context vector, learning to predict the target token index at the corresponding time step using a cross-entropy loss based on the target token index. The method also includes predicting speech recognition hypotheses for the utterance and training a multilingual automatic speech recognition (ASR) model using an unsupervised loss and a supervised loss.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.