System and method for speech recognition using machine transliteration and transfer learning
US12380289B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 1, 2022 |
| Grant date | Aug 5, 2025 |
| Priority date | — |
| Expiry date | Nov 18, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/0633
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for converting speech in one of a plurality of input languages into text using machine transliteration and transfer learning is disclosed. The method includes a training stage. The training stage includes receiving a training set of a plurality of audio files and an input text corresponding to the audio input in any input language using the speech recognition engine; transliterating the training set to transform the input text into transliterated text that includes characters of a base language and training acoustic model with the plurality of audio files and corresponding transliterated text using transfer learning. The method further includes an inference stage. The inference stage includes performing decoding on output of the trained acoustic model to generate text includes characters of the base language at inference and transliterating the generated text to output text includes characters in input language using reverse transliteration.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.