Concepedia

Attention-based Speech Recognition

Attention-Based Speech Recognition is a speech recognition framework that employs attention mechanisms to dynamically align and weight acoustic features over time, enabling more accurate and context-sensitive modeling of variable-length input sequences.

434

Publications

29.4K

Citations

1.2K

Authors

335

Institutions

Publications per year

2017–2026

404

Parents

Publications

434

Listen, attend and spell: A neural network for large vocabulary conversational speech recognition

William Chan, Navdeep Jaitly, Quoc V. Le et al. · 2016 · 2.3K citations

, , +15

Attention-Based Models for Speech Recognition

Jan Chorowski, Dzmitry Bahdanau, Dmitriy Serdyuk et al. · arXiv (Cornell University) · 2015 · 1.8K citations · Full text

, , +8

Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition

Linhao Dong, Shuang Xu, Bo Xu · 2018 · 1.1K citations

, , +14

Joint CTC-attention based end-to-end speech recognition using multi-task learning

Suyoun Kim, Takaaki Hori, Shinji Watanabe · 2017 · 906 citations

, , +16

Hybrid CTC/Attention Architecture for End-to-End Speech Recognition

Shinji Watanabe, Takaaki Hori, Suyoun Kim et al. · IEEE Journal of Selected Topics in Signal Processing · 2017 · 829 citations

, , +15

1–5 of 434

Authors

1.2K

  1. SW
    Shinji Watanabe

    Johns Hopkins University, United States

    31 publications · 3.6K citations

    22

    h-index

  2. TH
    Takaaki Hori

    Mitsubishi Electric (United States), United States

    22 publications · 2.9K citations

    18

    h-index

  3. JL
    Jinyu Li

    Microsoft (United States), United States

    15 publications · 914 citations

    14

    h-index

  4. YG
    Yashesh Gaur

    Microsoft (United States), United States

    11 publications · 501 citations

    11

    h-index

  5. JC
    Jan Chorowski

    University of Wrocław, Poland

    10 publications · 3.4K citations

    10

    h-index

1–5 of 1.2K

Institutions

335

  1. Google (United States)

    Mountain View, United States

    18 h-index

    127 publications

    18.3K citations

  2. Johns Hopkins University

    Baltimore, United States

    16 h-index

    42 publications

    2.2K citations

  3. Chinese Academy of Sciences

    Beijing, China

    16 h-index

    61 publications

    4.8K citations

  4. University of Chinese Academy of Sciences

    Beijing, China

    16 h-index

    38 publications

    2.4K citations

  5. Mitsubishi Electric (United States)

    Cypress, United States

    15 h-index

    43 publications

    5K citations

  6. Microsoft (United States)

    Redmond, United States

    13 h-index

    64 publications

    3.5K citations

  7. Northwestern Polytechnical University

    Xi'an, China

    13 h-index

    32 publications

    2.3K citations

  8. Tencent (China)

    Shenzhen, China

    11 h-index

    29 publications

    816 citations

1–8 of 335

Venues

  1. arXiv (Cornell University)

    Repository · 50 publications · 4.1K citations

    26

    h-index

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

    TASLP · 17 publications · 870 citations

    14

    h-index

  3. 10

    h-index

  4. 9

    h-index

  5. Sensors

    7 publications · 248 citations

    7

    h-index

1–5