Patent · US Active

Adaptive permutation invariant training with auxiliary information for monaural multi-talker speech recognition

US10699698B2 · kind B2 · utility

2Cited by

10References

19Claims

0Family size

Assignee

TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED · CN

Inventors

Yanmin QIAN · Shanghai, CN
Dong YU · Zhejiang, CN

Key dates

Filing date	Mar 29, 2018
Grant date	Jun 30, 2020
Priority date	—
Expiry date	Sep 4, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/02
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Provided are a speech recognition training processing method and an apparatus including the same. The speech recognition training processing method includes acquiring a stream of speech data from one or more speakers, extracting an auxiliary feature corresponding to a speech characteristic of the one or more speaker and updating an acoustic model by performing permutation invariant training (PIT) model training based on the auxiliary feature.

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