Training acoustic models using connectionist temporal classification
US11341958B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 16, 2020 |
| Grant date | May 24, 2022 |
| Priority date | — |
| Expiry date | Nov 27, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L2015/022
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training acoustic models and using the trained acoustic models. A connectionist temporal classification (CTC) acoustic model is accessed, the CTC acoustic model having been trained using a context-dependent state inventory generated from approximate phonetic alignments determined by another CTC acoustic model trained without fixed alignment targets. Audio data for a portion of an utterance is received. Input data corresponding to the received audio data is provided to the accessed CTC acoustic model. Data indicating a transcription for the utterance is generated based on output that the accessed CTC acoustic model produced in response to the input data. The data indicating the transcription is provided as output of an automated speech recognition service.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.