Patent · US Active

Multistage curriculum training framework for acoustic-to-word speech recognition

US11004443B2 · kind B2 · utility

4Cited by
4References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 30, 2018
Grant dateMay 11, 2021
Priority date
Expiry dateMar 9, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/045
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and apparatuses are provided for performing acoustic to word (A2W) speech recognition training performed by at least one processor. The method includes initializing, by the at least one processor, one or more first layers of a neural network with phone based Connectionist Temporal Classification (CTC), initializing, by the at least one processor, one or more second layers of the neural network with grapheme based CTC, acquiring, by the at least one processor, training data and performing, by the at least one processor, A2W speech recognition training based the initialized one or more first layers and one or more second layers of the neural network using the training data.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.