Patent · US Active

Method and device for speech processing

US11030991B2 · kind B2 · utility

0Cited by
1References
18Claims
0Family size

Assignee

Inventor

Key dates

Filing dateOct 4, 2019
Grant dateJun 8, 2021
Priority date
Expiry dateOct 4, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2015/223
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed are a speech processing method and a speech processing device, for performing speech processing by executing artificial intelligence (AI) algorithms and/or machine learning algorithms installed thereon, thus enabling the communication between a user terminal and a server in a 5G communication environment. The speech processing method according to an embodiment of the present disclosure includes receiving a user spoken utterance, outputting a voice actor spoken utterance in a voice actor's voice having the highest degree of similarity with a user's voice by using a user-voice actor mapping learning model, the voice actor spoken utterance corresponding to the user spoken utterance, and performing speech recognition for the voice actor spoken utterance.

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