Speech Enhancement via Combination of Wiener Filter and Blind Source Separation

被引：0

作者：

Hu, Hongmei ^{[1
,4
]}

Taghia, Jalil ^{[2
]}

Sang, Jinqiu ^{[1
]}

Taghia, Jalal ^{[3
]}

Mohammadiha, Nasser ^{[2
]}

Azarpour, Masoumeh ^{[3
]}

Dokku, Raiyalakshmi ^{[3
]}

Wang, Shouyan ^{[1
]}

Lutman, Mark E. ^{[1
]}

Bleeck, Stefan ^{[1
]}

机构：

[1] Univ Southampton, Inst Sound & Vibrat Res, Southampton, Hants, England

[2] Royal Inst Technol, Sch Elect Engn, Stockholm, Sweden

[3] Ruhr-Univ, Inst Commun Acoust, Bochum, Germany

[4] Jiangsu Univ, Dept Testing & Control, Zhenjiang, Peoples R China

来源：

PRACTICAL APPLICATIONS OF INTELLIGENT SYSTEMS | 2011年 / 124卷

关键词：

ASR; BWF; BSS;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Automatic speech recognition (ASR) often fails in acoustically noisy environments. Aimed to improve speech recognition scores of an ASR in a real-life like acoustical environment, a speech pre-processing system is proposed in this paper, which consists of several stages: First, a convolutive blind source separation (BSS) is applied to the spectrogram of the signals that are preprocessed by binaural Wiener filtering (BWF). Secondly, the target speech is detected by an ASR system recognition rate based on a Hidden Markov Model (HMM). To evaluate the performance of the proposed algorithm, the signal-to-interference ratio (SIR), the improvement signal-to-noise ratio (ISNR) and the speech recognition rates of the output signals were calculated using the signal corpus of the CHiME database. The results show an improvement in SIR and ISNR, but no obvious improvement of speech recognition scores. Improvements for future research are suggested.

引用

页码：485 / +

页数：3

共 50 条

[41] Speech enhancement using perceptual multi_band Wiener filter
Alaya, Sana
Zoghlami, Novlene
Lachiri, Zied
2014 1ST INTERNATIONAL CONFERENCE ON ADVANCED TECHNOLOGIES FOR SIGNAL AND IMAGE PROCESSING (ATSIP 2014), 2014, : 468 - 471
[42] SEMI-BLIND SPEECH ENHANCEMENT BASED ON RECURRENT NEURAL NETWORK FOR SOURCE SEPARATION AND DEREVERBERATION
Wake, Masaya
Bando, Yoshiaki
Mimura, Masato
Itoyama, Katsutoshi
Yoshii, Kazuyoshi
Kawahara, Tatsuya
2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2017,
[43] Blind Speech Separation and Enhancement With GCC-NMF
Wood, Sean U. N.
Rouat, Jean
Dupont, Stephane
Pironkov, Gueorgui
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2017, 25 (04) : 745 - 755
[44] Weibull and Nakagami speech priors based regularized NMF with adaptive wiener filter for speech enhancement
Jannu C.
Vanambathina S.D.
International Journal of Speech Technology, 2023, 26 (01) : 197 - 209
[45] A comprehensive approach to blind source separation of speech mixtures
2013, Institute of Electrical and Electronics Engineers Inc., United States
[46] Multistage Convolutive Blind Source Separation for Speech Mixture
Liang, Yanxue
Hagiwara, Ichiro
INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 2582 - 2585
[47] A speech encryption algorithm based on blind source separation
Lin, QH
Yin, FL
Mei, TM
Liang, HL
2004 INTERNATIONAL CONFERENCE ON COMMUNICATION, CIRCUITS, AND SYSTEMS, VOLS 1 AND 2: VOL 1: COMMUNICATION THEORY AND SYSTEMS, 2004, : 1013 - 1017
[48] Blind Source Separation of Noisy Mixed Speech Signals
Li, Huiya
Shi, Jianying
Men, Jinxi
SENSORS, MEASUREMENT AND INTELLIGENT MATERIALS II, PTS 1 AND 2, 2014, 475-476 : 291 - +
[49] A Comprehensive Approach to Blind Source Separation of Speech Mixtures
Zhao, Mengyi
He, Zhiming
2013 3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT), 2013, : 991 - 994
[50] Continuous speech segmentation determined by blind source separation
Szu, H
Hsu, C
Xie, DH
WAVELET APPLICATIONS V, 1998, 3391 : 396 - 408

← 1 2 3 4 5 →