Monaural speech separation based on MAXVQ and CASA for robust speech recognition

被引：32

作者：

Li, Peng ^{[1
]}

Guan, Yong ^{[2
]}

Wang, Shijin ^{[1
]}

Xu, Bo ^{[1
,2
]}

Liu, Wenju ^{[2
]}

机构：

[1] Chinese Acad Sci, Inst Automat, Digital Content Technol Res Ctr, Beijing 100190, Peoples R China

[2] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China

来源：

COMPUTER SPEECH AND LANGUAGE | 2010年 / 24卷 / 01期

关键词：

Monaural speech separation; Computational auditory scene analysis (CASA); Factorial-max vector quantization (MAXVQ); Automatic speech recognition (ASR); MAXIMUM-LIKELIHOOD-ESTIMATION; AUDITORY SCENE ANALYSIS; BIAS REMOVAL; NOISE; ADAPTATION;

D O I：

10.1016/j.csl.2008.05.005

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Robustness is one of the most important topics for automatic speech recognition (ASR) in practical applications. Monaural speech separation based on computational auditory scene analysis (CASA) offers a solution to this problem. In this paper, a novel system is presented to separate the monaural speech of two talkers. Gaussian mixture models (GMMs) and vector quantizers (VQs) are used to learn the grouping cues on isolated clean data for each speaker. Given an utterance, speaker identification is firstly performed to identify the two speakers presented in the utterance, then the factorial-max vector quantization model (MAXVQ) is used to infer the mask signals and finally the utterance of the target speaker is resynthesized in the CASA framework. Recognition results on the 2006 speech separation challenge corpus prove that this proposed system can improve the robustness of ASR significantly. (C) 2008 Elsevier Ltd. All rights reserved.

引用

页码：30 / 44

页数：15

共 50 条

[41] A new Genetic Algorithm based fusion scheme in monaural CASA system to improve the performance of the speech
S. Shoba
R. Rajavel
[J]. Journal of Ambient Intelligence and Humanized Computing, 2020, 11 : 433 - 446
[42] A new Genetic Algorithm based fusion scheme in monaural CASA system to improve the performance of the speech
Shoba, S.
Rajavel, R.
[J]. JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2020, 11 (01) : 433 - 446
[43] Speech parameters for the robust emotional speech recognition
Kim W.-G.
[J]. Journal of Institute of Control, Robotics and Systems, 2010, 16 (12) : 1137 - 1142
[44] Japanese speech databases for robust speech recognition
Nakamura, A
Matsunaga, S
Shimizu, T
Tonomura, M
Sagisaka, Y
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2199 - 2202
[45] Robust speech detector for speech recognition applications
Liang, WQ
Chen, YN
Shan, YX
Liu, J
Liu, RS
[J]. 2002 IEEE REGION 10 CONFERENCE ON COMPUTERS, COMMUNICATIONS, CONTROL AND POWER ENGINEERING, VOLS I-III, PROCEEDINGS, 2002, : 453 - 456
[46] Distilled Binary Neural Network for Monaural Speech Separation
Chen, Xiuyi
Liu, Guangcan
Shi, Jing
Xu, Jiaming
Xu, Bo
[J]. 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
[47] A Deep Ensemble Learning Method for Monaural Speech Separation
Zhang, Xiao-Lei
Wang, DeLiang
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2016, 24 (05) : 967 - 977
[48] On Synthesis for Supervised Monaural Speech Separation in Time Domain
Chen, Jingjing
Mao, Qirong
Liu, Dons
[J]. INTERSPEECH 2020, 2020, : 2627 - 2631
[49] Deep Attractor with Convolutional Network for Monaural Speech Separation
Lan, Tian
Qian, Yuxin
Tai, Wenxin
Chu, Boce
Liu, Qiao
[J]. 2020 11TH IEEE ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2020, : 40 - 44
[50] Investigation of Cost Function for Supervised Monaural Speech Separation
Liu, Yun
Zhang, Hui
Zhang, Xueliang
Cao, Yuhang
[J]. INTERSPEECH 2019, 2019, : 3178 - 3182

← 1 2 3 4 5 →