Detecting and recovering out-of-vocabulary words in voice-to-text transcription systems
US11183194B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 13, 2019 |
| Grant date | Nov 23, 2021 |
| Priority date | — |
| Expiry date | Mar 12, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/088
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Aspects of the present disclosure describe techniques for identifying and recovering out-of-vocabulary words in transcripts of a voice data recording using word recognition models and word sub-unit recognition models. An example method generally includes receiving a voice data recording for transcription into a textual representation of the voice data recording. The voice data recording is transcribed into the textual representation using a word recognition model. An unknown word is identified in the textual representation, and the unknown word is reconstructed based on recognition of sub-units of the unknown word generated by a sub-unit recognition model. The textual representation of the voice data recording is modified by replacing the unknown word with the reconstruction of the unknown word, and the modified textual representation is output.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.