Audio-Visual Efficient Conformer for Robust Speech Recognition

被引:15
|
作者
Burchi, Maxime [1 ]
Timofte, Radu [1 ]
机构
[1] Univ Wurzburg, Comp Vis Lab, IFI, Wurzburg, Germany
关键词
D O I
10.1109/WACV56688.2023.00229
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
End-to-end Automatic Speech Recognition (ASR) systems based on neural networks have seen large improvements in recent years. The availability of large scale hand-labeled datasets and sufficient computing resources made it possible to train powerful deep neural networks, reaching very low Word Error Rate (WER) on academic benchmarks. However, despite impressive performance on clean audio samples, a drop of performance is often observed on noisy speech. In this work, we propose to improve the noise robustness of the recently proposed Efficient Conformer Connectionist Temporal Classification (CTC)-based architecture by processing both audio and visual modalities. We improve previous lip reading methods using an Efficient Conformer back-end on top of a ResNet-18 visual front-end and by adding intermediate CTC losses between blocks. We condition intermediate block features on early predictions using Inter CTC residual modules to relax the conditional independence assumption of CTC-based models. We also replace the Efficient Conformer grouped attention by a more efficient and simpler attention mechanism that we call patch attention. We experiment with publicly available Lip Reading Sentences 2 (LRS2) and Lip Reading Sentences 3 (LRS3) datasets. Our experiments show that using audio and visual modalities allows to better recognize speech in the presence of environmental noise and significantly accelerate training, reaching lower WER with 4 times less training steps. Our Audio-Visual Efficient Conformer (AVEC) model achieves state-of-the-art performance, reaching WER of 2.3% and 1.8% on LRS2 and LRS3 test sets. Code and pretrained models are available at https://github.com/burchim/AVEC.
引用
收藏
页码:2257 / 2266
页数:10
相关论文
共 50 条
  • [21] Audio-Visual Speech Modeling for Continuous Speech Recognition
    Dupont, Stephane
    Luettin, Juergen
    IEEE TRANSACTIONS ON MULTIMEDIA, 2000, 2 (03) : 141 - 151
  • [22] Resource-efficient TDNN Architectures for Audio-visual Speech Recognition
    Koumparoulis, Alexandros
    Potamianos, Gerasimos
    Thomas, Samuel
    Morais, Edmilson da Silva
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 506 - 510
  • [23] MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation
    Anwar, Mohamed
    Shi, Bowen
    Goswami, Vedanuj
    Hsu, Wei-Ning
    Pino, Juan
    Wang, Changhan
    INTERSPEECH 2023, 2023, : 4064 - 4068
  • [24] A ROBUST AUDIO-VISUAL SPEECH ENHANCEMENT MODEL
    Wang, Wupeng
    Xing, Chao
    Wang, Dong
    Chen, Xiao
    Sun, Fengyu
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 7529 - 7533
  • [25] Speaker independent audio-visual speech recognition
    Zhang, Y
    Levinson, S
    Huang, T
    2000 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, PROCEEDINGS VOLS I-III, 2000, : 1073 - 1076
  • [26] A coupled HMM for audio-visual speech recognition
    Nefian, AV
    Liang, LH
    Pi, XB
    Xiaoxiang, L
    Mao, C
    Murphy, K
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 2013 - 2016
  • [27] An asynchronous DBN for audio-visual speech recognition
    Saenko, Kate
    Livescu, Karen
    2006 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, 2006, : 154 - +
  • [28] Audio-visual modeling for bimodal speech recognition
    Kaynak, MN
    Zhi, Q
    Cheok, AD
    Sengupta, K
    Chung, KC
    2001 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5: E-SYSTEMS AND E-MAN FOR CYBERNETICS IN CYBERSPACE, 2002, : 181 - 186
  • [29] Multistream sparse representation features for noise robust audio-visual speech recognition
    Shen, Peng
    Tamura, Satoshi
    Hayamizu, Satoru
    ACOUSTICAL SCIENCE AND TECHNOLOGY, 2014, 35 (01) : 17 - 27
  • [30] Bimodal fusion in audio-visual speech recognition
    Zhang, XZ
    Mersereau, RM
    Clements, M
    2002 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL I, PROCEEDINGS, 2002, : 964 - 967