Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DISTRIBUTED SPEECH PROCESSING SYSTEM AND METHOD
Document Type and Number:
WIPO Patent Application WO/2022/144009
Kind Code:
A1
Abstract:
Provided are a distributed speech processing system and method. The system comprises: multiple node devices in a network, where each node device comprises a processor, a memory, a communication module, and a sound processing module, and at least one node device comprises a sound capturing module, wherein the sound capturing module is configured to capture an audio signal. The sound processing module is configured to preprocess the audio signal to produce a first sound preprocessing result. The communication module is configured to transmit the first sound preprocessing result to one or more node devices in the network. The communication module is also configured to receive from the network one or more second sound preprocessing results from at least one other node device; and the sound processing module is also configured to execute speech recognition on the basis of the first sound preprocessing result and/or of the one or more second sound preprocessing results. The present application implements a decentralized design, increases the efficiency, stability, and robustness of speech recognition.

Inventors:
MAO JIANXIN (CN)
Application Number:
PCT/CN2021/143983
Publication Date:
July 07, 2022
Filing Date:
December 31, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
ESPRESSIF SYS SHANGHAI CO LTD (CN)
International Classes:
G10L15/30; G10L15/02; G10L15/32
Foreign References:
CN112652310A2021-04-13
CN105206281A2015-12-30
CN110310637A2019-10-08
CN110838286A2020-02-25
CN107925818A2018-04-17
CN110136708A2019-08-16
CN110046222A2019-07-23
US20180190292A12018-07-05
US5430730A1995-07-04
Attorney, Agent or Firm:
BEIJING LUSHENG LAW FIRM (CN)
Download PDF: