Title:
NEURAL NETWORK SPEECH RECOGNITION METHOD AND SYSTEM ORIENTED TO HOME SPOKEN ENVIRONMENT
Document Type and Number:
WIPO Patent Application WO/2021/208455
Kind Code:
A1
Abstract:
A neural network speech recognition method and system oriented to a home spoken environment, comprising: model construction: adding a long-short-term memory network into a deep neural network, to construct a combined neural network DNN-LSTM model; pre-processing an acquired speech data set to obtain a feature vector set, and using the feature vector set as an input of the DNN-LSTM model to perform iterative training, so as to train same to an optimal acoustic model; causing an input speech signal of an unknown language to be subjected to the trained DNN-LSTM model to respectively obtain a Chinese output probability vector set and an English output probability vector set; performing language matching according to the Chinese output probability vector set and the English output probability vector set, and outputting a determination result. The present invention is able to quickly and accurately recognize content of a speaker in a home scene, and can be widely applied to an actual home scene.
Inventors:
ZHANG HUI (CN)
CHENG MING (CN)
ZHAO HAITAO (CN)
SUN YANFEI (CN)
NI YIYANG (CN)
ZHU HONGBO (CN)
CHENG MING (CN)
ZHAO HAITAO (CN)
SUN YANFEI (CN)
NI YIYANG (CN)
ZHU HONGBO (CN)
Application Number:
PCT/CN2020/133554
Publication Date:
October 21, 2021
Filing Date:
December 03, 2020
Export Citation:
Assignee:
UNIV NANJING POSTS & TELECOMMUNICATIONS (CN)
International Classes:
G10L15/16; G10L15/00; G10L15/06
Domestic Patent References:
WO2019006473A1 | 2019-01-03 |
Foreign References:
CN108389573A | 2018-08-10 | |||
CN111477220A | 2020-07-31 | |||
CN108335693A | 2018-07-27 | |||
CN110517668A | 2019-11-29 |
Other References:
ZHAO SHUFANG;DONG XIAOYU: "Research on Speech Recognition Based on Improved LSTM Deep Neural Network", JOURNAL OF ZHENGZHOU UNIVERSITY(ENGINEERING SCIENCE), vol. 39, no. 5, 19 July 2018 (2018-07-19), pages 63 - 67, XP055857765, ISSN: 1671-6833, DOI: 10.13708/j.issn.1671-6833.2018.02.004
Attorney, Agent or Firm:
NANJING SUGAO PATENT AND TRADEMARK FIRM (ORDINARY PARTNERSHIP) (CN)
Download PDF: