EXEMPLAR-BASED NOISE ROBUST AUTOMATIC SPEECH RECOGNITION USING MODULATION SPECTROGRAM FEATURES

被引：0

作者：

Baby, Deepak ^{[1
]}

Virtanen, Tuomas ^{[2
]}

Gemmeke, Jort F. ^{[1
]}

Barker, Tom ^{[2
]}

Van Hamme, Hugo ^{[1
]}

机构：

[1] Katholieke Univ Leuven, Dept ESAT, Leuven, Belgium

[2] Tampere Univ Technol, Dept Signal Proc, FIN-33101 Tampere, Finland

来源：

2014 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY SLT 2014 | 2014年

关键词：

modulation envelope; coupled dictionaries; non-negative matrix factorisation; automatic speech recognition; REPRESENTATION;

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：

We propose a novel exemplar-based feature enhancement method for automatic speech recognition which uses coupled dictionaries: an input dictionary containing atoms sampled in the modulation (envelope) spectrogram domain and an output dictionary with atoms in the Mel or full-resolution frequency domain. The input modulation representation is chosen for its separation properties of speech and noise and for its relation with human auditory processing. The output representation is one which can be processed by the ASR backend. The proposed method was investigated on the AURORA-2 and AURORA-4 databases and improved word error rates (WER) were obtained when compared to the system which uses Mel features in the input exemplars. The paper also proposes a hybrid system which combines the baseline and the proposed algorithm on the AURORA-2 database which in turn also yielded improvement over both the algorithms.

引用

页码：519 / 524

页数：6

共 50 条

[1] Exemplar-Based Sparse Representations for Noise Robust Automatic Speech Recognition
Gemmeke, Jort F.
Virtanen, Tuomas
Hurmalainen, Antti
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (07): : 2067 - 2080
[2] HYBRID INPUT SPACES FOR EXEMPLAR-BASED NOISE ROBUST SPEECH RECOGNITION USING COUPLED DICTIONARIES
Baby, Deepak
Van Hamme, Hugo
[J]. 2015 23RD EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2015, : 1676 - 1680
[3] NOISE ROBUST EXEMPLAR-BASED CONNECTED DIGIT RECOGNITION
Gemmeke, Jort F.
Virtanen, Tuomas
[J]. 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4546 - 4549
[4] SEMI-SUPERVISED NOISE DICTIONARY ADAPTATION FOR EXEMPLAR-BASED NOISE ROBUST SPEECH RECOGNITION
Luan, Yi
Saito, Daisuke
Kashiwagi, Yosuke
Minematsu, Nobuaki
Hirose, Keikichi
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[5] Estimating Uncertainty to Improve Exemplar-Based Feature Enhancement for Noise Robust Speech Recognition
Kallasjoki, Heikki
Gemmeke, Jort F.
Palomaki, Kalle J.
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2014, 22 (02) : 368 - 380
[6] Noise robust Automatic Speech Recognition system by integrating Robust Principal Component Analysis (RPCA) and Exemplar-based Sparse Representation
Gavrilescu, Mihai
[J]. PROCEEDINGS OF THE 2015 7TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE (ECAI), 2015, : S29 - S33
[7] Coupled Dictionaries for Exemplar-Based Speech Enhancement and Automatic Speech Recognition
Baby, Deepak
Virtanen, Tuomas
Gemmeke, Jort F.
van Hamme, Hugo
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2015, 23 (11) : 1788 - 1799
[8] Robust speech recognition using the modulation spectrogram
Kingsbury, BED
Morgan, N
Greenberg, S
[J]. SPEECH COMMUNICATION, 1998, 25 (1-3) : 117 - 132
[9] Advances in noise robust digit recognition using hybrid exemplar-based techniques
Gemmeke, Jort F.
Van Hamme, Hugo
[J]. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 2131 - 2134
[10] NOISE-ROBUST SPEECH RECOGNITION WITH EXEMPLAR-BASED SPARSE REPRESENTATIONS USING ALPHA-BETA DIVERGENCE
Yilmaz, Emre
Gemmeke, Jort F.
Van Hamme, Hugo
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,

← 1 2 3 4 5 →