Title:
SPEECH PROCESSING METHOD AND APPARATUS, AND STORAGE MEDIUM, COMPUTER DEVICE AND PROGRAM PRODUCT
Document Type and Number:
WIPO Patent Application WO/2023/216760
Kind Code:
A1
Abstract:
Disclosed in the present application are a speech processing method and apparatus, and a storage medium, a computer device and a program product. The method comprises: acquiring initial speech features of call speech; inputting the initial speech features into a pre-trained speech enhancement model, so as to obtain target speech features, which are output by the speech enhancement model, wherein the speech enhancement model is obtained by means of step-by-step training on the basis of a deep clustering loss function and a mask inference loss function; and according to the target speech features, calculating target speech with noise and reverberation removed.
More Like This:
| WO/2019/245916 | METHOD AND SYSTEM FOR PARAMETRIC SPEECH SYNTHESIS |
| JPH11311992 | SPEECH RECOGNISION METHOD |
| JP4710130 | Audio signal separation method and equipment |
Inventors:
HUANG JUN (CN)
WANG YANNAN (CN)
WANG YANNAN (CN)
Application Number:
PCT/CN2023/085321
Publication Date:
November 16, 2023
Filing Date:
March 31, 2023
Export Citation:
Assignee:
TENCENT TECH SHENZHEN CO LTD (CN)
International Classes:
G10L15/02; G10L15/06; G10L21/0208
Foreign References:
| CN110176243A | 2019-08-27 | |||
| CN110600017A | 2019-12-20 | |||
| US20200066296A1 | 2020-02-27 | |||
| US20210074282A1 | 2021-03-11 |
Attorney, Agent or Firm:
CHINA PAT INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF: