Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
SPEECH ENHANCEMENT METHOD, APPARATUS AND SYSTEM, AND COMPUTER-READABLE STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/160593
Kind Code:
A1
Abstract:
A speech enhancement method, apparatus and system, and a computer-readable storage medium. The method comprises: acquiring a time-domain microphone signal and a time-domain bone conduction signal at the current moment (S110); determining whether the time-domain microphone signal and the time-domain bone conduction signal are speech signals (S120); if so, performing noise cancellation processing on the time-domain microphone signal by means of a pre-established DNN noise cancellation model, and performing frequency-domain noise cancellation processing on the time-domain bone conduction signal (S130); if not, setting an output signal corresponding to the current moment to be zero (S140); performing high-pass filtering processing on the time-domain microphone signal that has been subjected to noise cancellation, so as to obtain a first output time-domain signal, and performing low-pass filtering processing on the time-domain bone conduction signal that has been subjected to noise cancellation, so as to obtain a second output time-domain signal (S150); and according to the first output time-domain signal and the second output time-domain signal, obtaining an output time-domain signal corresponding to the current moment (S160). By means of the method, background noise can be better cancelled, which is conducive to improving the sound quality, and enhancing the user experience.

Inventors:
CHEN, Guoming (CN)
Application Number:
PCT/CN2021/103635
Publication Date:
August 04, 2022
Filing Date:
June 30, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
GOERTEK INC. (CN)
International Classes:
G10L21/0224
Download PDF: