Patent · US Active

Token-wise training for attention based end-to-end speech recognition

US11037547B2 · kind B2 · utility

1Cited by
0References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 14, 2019
Grant dateJun 15, 2021
Priority date
Expiry dateAug 23, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/082
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method of attention-based end-to-end (A-E2E) automatic speech recognition (ASR) training, includes performing cross-entropy training of a model, based on one or more input features of a speech signal, determining a posterior probability vector at a time of a first wrong token among one or more output tokens of the model of which the cross-entropy training is performed, and determining a loss of the first wrong token at the time, based on the determined posterior probability vector. The method further includes determining a total loss of a training set of the model of which the cross-entropy training is performed, based on the determined loss of the first wrong token, and updating the model of which the cross-entropy training is performed, based on the determined total loss of the training set.

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