Title:
SPEECH RECOGNITION METHOD, APPARATUS AND DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/035397
Kind Code:
A1
Abstract:
Provided in the present application are a speech recognition method, apparatus and device, and a storage medium. The method comprises: acquiring a speech feature of target mixed speech and a speaker feature of a specified speaker; taking the direction of tending to a target speech feature as an extraction direction, and according to the speech feature of the target mixed speech and a speaker feature of a target speaker, extracting a speech feature of the target speaker from the speech feature of the target mixed speech, so as to obtain an extracted speech feature of the target speaker, wherein the target speech feature is a speech feature that is used to obtain a speech recognition result consistent with real speech content of the target speaker; and acquiring a speech recognition result of the specified speaker according to an extracted speech feature of the specified speaker. By means of the speech recognition method provided in the present application, speech content of a specified speaker can be recognized more accurately from mixed speech including speech of the specified speaker, thereby achieving a better user experience.
Inventors:
FANG XIN (CN)
LIU JUNHUA (CN)
LIU JUNHUA (CN)
Application Number:
PCT/CN2021/129733
Publication Date:
March 16, 2023
Filing Date:
November 10, 2021
Export Citation:
Assignee:
IFLYTEK CO LTD (CN)
International Classes:
G10L17/02; G10L17/04; G10L25/24; G10L25/30; G10L25/51
Foreign References:
| CN110827853A | 2020-02-21 | |||
| CN110288989A | 2019-09-27 | |||
| CN111128197A | 2020-05-08 | |||
| CN109874096A | 2019-06-11 | |||
| CN111433847A | 2020-07-17 | |||
| CN202111042821A | 2021-09-07 |
Attorney, Agent or Firm:
UNITALEN ATTORNEYS AT LAW (CN)
Download PDF: