Patent · US Active

Training acoustic models using connectionist temporal classification

US10229672B1 · kind B1 · utility

30Cited by
60References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 3, 2017
Grant dateMar 12, 2019
Priority date
Expiry dateJan 3, 2037

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.