Systems and methods for a multilingual speech recognition framework
US11798534B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 29, 2021 |
| Grant date | Oct 24, 2023 |
| Priority date | — |
| Expiry date | Dec 31, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0631
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments described herein provide an Adapt-and-Adjust (A2) mechanism for multilingual speech recognition model that combines both adaptation and adjustment methods as an integrated end-to-end training to improve the models' generalization and mitigate the long-tailed issue. Specifically, a multilingual language model mBERT is utilized, and converted into an autoregressive transformer decoder. In addition, a cross-attention module is added to the encoder on top of the mBERT's self-attention layer in order to explore the acoustic space in addition to the text space. The joint training of the encoder and mBERT decoder can bridge the semantic gap between the speech and the text.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.