Title:
DATA PROCESSING METHOD AND APPARATUS
Document Type and Number:
WIPO Patent Application WO/2024/046473
Kind Code:
A1
Abstract:
A data processing method, which is applied to action generation implemented on the basis of speech or text. The method comprises: acquiring speech data; determining a plurality of segmentation point positions from the speech data according to audio features of the speech data, wherein the segmentation point positions correspond to predicted rhythm points of a body action made by a character object when the character object emits the speech data; obtaining a feature representation by means of a feature extraction network according to the speech data and information that indicates the plurality of segmentation point positions; and generating action data by means of an action generation network according to the feature representation. By means of the present application, a generated action can have an accurate sense of rhythm, such that the action more closely resembles an action of a character object when the character object actually speaks.
Inventors:
AO TENGLONG (CN)
LIU LIBIN (CN)
LOU YUKE (CN)
CHEN BAOQUAN (CN)
ZHANG ZHENSONG (CN)
XU SONGCEN (CN)
WU XIAOFEI (CN)
LIU LIBIN (CN)
LOU YUKE (CN)
CHEN BAOQUAN (CN)
ZHANG ZHENSONG (CN)
XU SONGCEN (CN)
WU XIAOFEI (CN)
Application Number:
PCT/CN2023/116552
Publication Date:
March 07, 2024
Filing Date:
September 01, 2023
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
H04N21/233; G10L15/04; G10L15/16; H04N21/234; H04N21/439; H04N21/44
Foreign References:
| CN114911973A | 2022-08-16 | |||
| CN115866291A | 2023-03-28 | |||
| CN113763532A | 2021-12-07 | |||
| CN113192161A | 2021-07-30 | |||
| CN113750523A | 2021-12-07 | |||
| US20200265836A1 | 2020-08-20 |
Attorney, Agent or Firm:
SHENPAT INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF:
Previous Patent: FLIP-IN VEHICLE DOOR HANDLE, VEHICLE DOOR, AND VEHICLE
Next Patent: METHOD FOR DETECTING CAR COPY NUMBER
Next Patent: METHOD FOR DETECTING CAR COPY NUMBER