The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Mar. 10, 2026

Filed:

Feb. 24, 2022
Applicant:

Tencent Technology (Shenzhen) Company Limited, Shenzhen, CN;

Inventors:

Wei Xiao, Shenzhen, CN;

Qingbo Huang, Shenzhen, CN;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G10L 19/02 (2013.01); G06N 3/044 (2023.01); G06N 3/0442 (2023.01); G06N 3/045 (2023.01); G06N 3/09 (2023.01); G10L 19/00 (2013.01); G10L 19/002 (2013.01); G10L 19/008 (2013.01); G10L 19/032 (2013.01); G10L 19/06 (2013.01); G10L 19/16 (2013.01); G10L 19/26 (2013.01); G10L 21/038 (2013.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01);
U.S. Cl.
CPC ...
G10L 19/0208 (2013.01); G06N 3/0442 (2023.01); G06N 3/045 (2023.01); G06N 3/09 (2023.01); G10L 19/00 (2013.01); G10L 19/008 (2013.01); G10L 19/06 (2013.01); G10L 21/038 (2013.01); G10L 25/18 (2013.01); G10L 25/30 (2013.01); G06N 3/044 (2023.01); G10L 19/002 (2013.01); G10L 19/02 (2013.01); G10L 19/0204 (2013.01); G10L 19/032 (2013.01); G10L 19/16 (2013.01); G10L 19/26 (2013.01);
Abstract

Embodiments of the disclosure provide a speech signal encoding and decoding methods and apparatuses, an electronic device, and a computer-readable storage medium. The decoding method includes: obtaining a bitstream including a first substream, and the first substream being a bitstream obtained by encoding a low-frequency subband signal of an original speech signal by using a first encoding method; and performing signal reconstruction based on the first substream in a case that the bitstream includes no second substream, to obtain a reconstructed speech signal; or performing signal reconstruction based on the first substream and at least one second substream in a case that the bitstream includes the at least one second substream, to obtain a reconstructed speech signal, each second sub stream being obtained by encoding a high-frequency subband signal of the original speech signal, and the encoding being performed by using a second encoding method corresponding to the each second substream.


Find Patent Forward Citations

Loading…