Open AccessThe Software System Implementation of Speech Command Recognizer Under Intensive Background Nosie
Author(s) -
Jingyu Song,
Bin Chen,
Kun Jiang,
Miaosheng Yang,
Xi Xiao
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/563/5/052090
Subject(s) - speech recognition , computer science , hidden markov model , voice activity detection , noise (video) , software , word (group theory) , linear predictive coding , background noise , signal (programming language) , sampling (signal processing) , speech processing , artificial intelligence , filter (signal processing) , computer vision , telecommunications , linguistics , philosophy , image (mathematics) , programming language
A device for speech command recognition is designed and implemented in this paper. The adaptive filtering technique is adopted for speech enhancement by using two microphones for sampling the background noise and noisy speech signal correspondently. The connected-word speech recognition algorithm based on HMM is employed for speech command recognition. The experiment shows that the equipment can work well under the background noise of 90dB.