Concepedia

Audio-visual Speech Recognition

Audio-Visual Speech Recognition is a computational framework that integrates auditory and visual speech signals to improve speech recognition accuracy by leveraging temporal and cross-modal correspondences between lip movements and acoustic patterns.

902

Publications

59.3K

Citations

2.1K

Authors

660

Institutions

Publications per year

2017–2026

316

Variants

Avsr

Parents

Publications

902

Hearing lips and seeing voices

Harry McGurk, John MacDonald · Nature · 1976 · 6.1K citations

, , +10

Multimodal Deep Learning

Jiquan Ngiam, Aditya Khosla, Mingyu Kim et al. · 2011 · 2.3K citations

, , +15

VoxCeleb2: Deep Speaker Recognition

Joon Son Chung, Arsha Nagrani, Andrew Zisserman · 2018 · 2.3K citations · Full text

, , +14

An audio-visual corpus for speech perception and automatic speech recognition

Martin Cooke, Jon Barker, Stuart Cunningham et al. · The Journal of the Acoustical Society of America · 2006 · 1.2K citations

, , +17

Synthesizing Obama

Supasorn Suwajanakorn, Steven M. Seitz, Ira Kemelmacher-Shlizerman · ACM Transactions on Graphics · 2017 · 1.1K citations

, , +16

1–5 of 902

Authors

2.1K

  1. CN
    C. Neti

    IBM Research - Thomas J. Watson Research Center, United States

    32 publications · 2.3K citations

    25

    h-index

  2. GP
    Gerasimos Potamianos

    IBM Research - Thomas J. Watson Research Center, United States

    36 publications · 1.7K citations

    25

    h-index

  3. MP
    Maja Pantić

    Imperial College London, United Kingdom

    17 publications · 942 citations

    13

    h-index

  4. SP
    Stavros Petridis

    Imperial College London, United Kingdom

    17 publications · 942 citations

    13

    h-index

  5. AZ
    Andrew Zisserman

    University of Oxford, United Kingdom

    11 publications · 3.8K citations

    11

    h-index

1–5 of 2.1K

Institutions

660

  1. IBM Research - Thomas J. Watson Research Center

    Yorktown Heights, United States

    20 h-index

    76 publications

    4.5K citations

  2. Carnegie Mellon University

    Pittsburgh, United States

    19 h-index

    37 publications

    1.9K citations

  3. Centre National de la Recherche Scientifique

    Paris, France

    18 h-index

    56 publications

    2.6K citations

  4. Google (United States)

    Mountain View, United States

    16 h-index

    66 publications

    7.4K citations

  5. Imperial College London

    London, United Kingdom

    15 h-index

    48 publications

    2.9K citations

  6. Queensland University of Technology

    Brisbane, Australia

    15 h-index

    42 publications

    1.1K citations

  7. University of Illinois Urbana-Champaign

    Urbana, United States

    14 h-index

    30 publications

    1.7K citations

  8. IBM (United States)

    Armonk, United States

    14 h-index

    49 publications

    4.9K citations

1–8 of 660

Venues

  1. IEEE Transactions on Multimedia

    19 publications · 1.9K citations

    17

    h-index

  2. arXiv (Cornell University)

    Repository · 28 publications · 985 citations

    16

    h-index

  3. IEEE/ACM Transactions on Audio Speech and Language Processing

    TASLP · 17 publications · 686 citations

    15

    h-index

  4. Speech Communication

    16 publications · 596 citations

    13

    h-index

  5. The Journal of the Acoustical Society of America

    JASA · 16 publications · 2.3K citations

    13

    h-index

1–5