Patent · US Active

Method and apparatus for multi-lingual end-to-end speech recognition

US10593321B2 · kind B2 · utility

4Cited by
1References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 15, 2017
Grant dateMar 17, 2020
Priority date
Expiry dateDec 23, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/005
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for training a multi-language speech recognition network includes providing utterance datasets corresponding to predetermined languages, inserting language identification (ID) labels into the utterance datasets, wherein each of the utterance datasets is labelled by each of the language ID labels, concatenating the labeled utterance datasets, generating initial network parameters from the utterance datasets, selecting the initial network parameters according to a predetermined sequence, and training, iteratively, an end-to-end network with a series of the selected initial network parameters and the concatenated labeled utterance datasets until a training result reaches a threshold.

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