EXTRACTING DEEP BOTTLENECK FEATURES FOR VISUAL SPEECH RECOGNITION

被引：0

作者：

Sui, Chao ^{[1
]}

Togneri, Roberto ^{[2
]}

Bennamoun, Mohammed ^{[1
]}

机构：

[1] Univ Western Australia, Sch Comp Sci & Software Engn, Nedlands, WA, Australia

[2] Univ Western Australia, Sch Elect Elect & Comp Engn, Nedlands, WA, Australia

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP) | 2015年

关键词：

Visual speech recognition; stacked denoising auto-encoder; deep bottleneck feature;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Motivated by the recent progresses in the use of deep learning techniques for acoustic speech recognition, we present in this paper a visual deep bottleneck feature (DBNF) learning scheme using a stacked auto-encoder combined with other techniques. Experimental results show that our proposed deep feature learning scheme yields approximately 24% relative improvement for visual speech accuracy. To the hest of our knowledge, this is the first study which uses deep bottleneck feature on visual speech recognition. Our work firstly shows that the deep bottleneck visual feature is able to achieve a significant accuracy improvement on visual speech recognition.

引用

页码：1518 / 1522

页数：5

共 50 条

[1] DEEP COMPLEMENTARY BOTTLENECK FEATURES FOR VISUAL SPEECH RECOGNITION
Petridis, Stavros
Pantic, Maja
[J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 2304 - 2308
[2] Integration of Deep Bottleneck Features for Audio-Visual Speech Recognition
Ninomiya, Hiroshi
Kitaoka, Norihide
Tamura, Satoshi
Iribe, Yurie
Takeda, Kazuya
[J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 563 - 567
[3] Audio-visual speech recognition using deep bottleneck features and high-performance lipreading
Tamura, Satoshi
Ninomiya, Hiroshi
Kitaoka, Norihide
Osuga, Shin
Iribe, Yurie
Takeda, Kazuya
Hayamizu, Satoru
[J]. 2015 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2015, : 575 - 582
[4] Robust speech recognition by extracting invariant features
Eskikand, Parvin Zarei
Seyyedsalehi, Seyyed Ali
[J]. 4TH INTERNATIONAL CONFERENCE OF COGNITIVE SCIENCE, 2012, 32 : 230 - 237
[5] ON THE USEFULNESS OF STATISTICAL NORMALISATION OF BOTTLENECK FEATURES FOR SPEECH RECOGNITION
Loweimi, Erfan
Bell, Peter
Renals, Steve
[J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 3862 - 3866
[6] Noisy speech recognition using blind spatial subtraction array technique and deep bottleneck features
Kitaoka, Norihide
Hayashi, Tomoki
Takeda, Kazuya
[J]. 2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,
[7] INCOHERENT TRAINING OF DEEP NEURAL NETWORKS TO DE-CORRELATE BOTTLENECK FEATURES FOR SPEECH RECOGNITION
Bao, Yebo
Jiang, Hui
Dai, Lirong
Liu, Cong
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 6980 - 6984
[8] LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION BASED ON WFST STRUCTURED CLASSIFIERS AND DEEP BOTTLENECK FEATURES
Kubo, Yotaro
Hori, Takaaki
Nakamura, Atsushi
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7629 - 7633
[9] EXTRACTING DEEP BOTTLENECK FEATURES USING STACKED AUTO-ENCODERS
Gehring, Jonas
Miao, Yajie
Metze, Florian
Waibel, Alex
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 3377 - 3381
[10] Articulatory and Stacked Bottleneck Features for Low Resource Speech Recognition
Shetty, Vishwas M.
Sharon, Rini A.
Abraham, Basil
Seeram, Tejaswi
Prakash, Anusha
Ravi, Nithya
Umesh, S.
[J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3202 - 3206

← 1 2 3 4 5 →