Title:
AUDIO PROCESSING METHOD AND APPARATUS, DEVICE, READABLE STORAGE MEDIUM, AND PROGRAM PRODUCT
Document Type and Number:
WIPO Patent Application WO/2024/051481
Kind Code:
A1
Abstract:
An audio processing method and apparatus, a device, a readable storage medium, and a program product, relating to the technical field of computers. The method comprises: determining voiceprint vectors respectively corresponding to a plurality of audio clips, the voiceprint vectors being used for indicating voiceprint features corresponding to the audio clips (201); determining an initial similarity matrix according to the voiceprint vectors corresponding to the audio clips, the initial similarity matrix comprising the similarity between the voiceprint vectors corresponding to any two audio clips (202); adjusting the initial similarity matrix according to dynamic thresholds corresponding to rows in the initial similarity matrix to obtain a reference similarity matrix (203); determining the number of audio objects in the plurality of audio clips according to the reference similarity matrix (204); and performing clustering on the plurality of audio clips according to the number of audio objects to obtain audio clips corresponding to the audio objects (205).
Inventors:
ZHU HONGNING (CN)
Application Number:
PCT/CN2023/114040
Publication Date:
March 14, 2024
Filing Date:
August 21, 2023
Export Citation:
Assignee:
TENCENT TECH SHENZHEN CO LTD (CN)
International Classes:
G06F16/65; G10L25/27
Domestic Patent References:
| WO2021072893A1 | 2021-04-22 |
Foreign References:
| CN115168643A | 2022-10-11 | |||
| CN114446284A | 2022-05-06 | |||
| CN113327628A | 2021-08-31 | |||
| CN114822558A | 2022-07-29 |
Attorney, Agent or Firm:
BEIJING SAN GAO YONG XIN INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: