Concepedia

Self-supervised Speech Representation Learning

Self-Supervised Speech Representation Learning is a machine learning paradigm that belongs to the broader category of speech representation learning, distinguished by its use of unlabeled speech data to pre-train models through pretext tasks that exploit intrinsic structural information within the audio signal for the purpose of deriving generalizable and transferable acoustic features.

196

Publications

15K

Citations

630

Authors

181

Institutions

Publications per year

2017–2026

194

Parents

Publications

196

In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication

arXiv (Cornell University) · 2020 · 2.4K citations · Full text

, , +16

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

Sanyuan Chen, Chengyi Wang, Zhengyang Chen et al. · IEEE Journal of Selected Topics in Signal Processing · 2022 · 1.7K citations · Full text

, , +14

SUPERB: Speech Processing Universal PERformance Benchmark

Shu-Wen Yang, Po-Han Chi, Yung-Sung Chuang et al. · 2021 · 637 citations

, , +11

XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale

Arun Babu, Changhan Wang, Andros Tjandra et al. · Interspeech 2022 · 2022 · 519 citations

, , +14

wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations

Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed et al. · Neural Information Processing Systems · 2020 · 407 citations

, , +12

1–5 of 196

Authors

630

  1. HL
    Hung-yi Lee

    National Taiwan University, Taiwan

    20 publications · 1.7K citations

    17

    h-index

  2. SW
    Shinji Watanabe

    Johns Hopkins University, United States

    15 publications · 1.1K citations

    15

    h-index

  3. AB
    Alexei Baevski

    Meta (Israel), Israel

    16 publications · 2.2K citations

    15

    h-index

  4. WH
    Wei-Ning Hsu

    Massachusetts Institute of Technology, United States

    12 publications · 1.2K citations

    12

    h-index

  5. MA
    Michael Auli

    Meta (Israel), Israel

    13 publications · 2K citations

    12

    h-index

1–5 of 630

Institutions

181

  1. National Taiwan University

    Taipei, Taiwan

    17 h-index

    74 publications

    10.6K citations

  2. Carnegie Mellon University

    Pittsburgh, United States

    12 h-index

    39 publications

    2.9K citations

  3. Meta (Israel)

    Tel Aviv, Israel

    12 h-index

    43 publications

    4.1K citations

  4. Johns Hopkins University

    Baltimore, United States

    9 h-index

    23 publications

    2.1K citations

  5. Chinese Academy of Sciences

    Beijing, China

    9 h-index

    15 publications

    1.1K citations

  6. Amazon (United States)

    Seattle, United States

    8 h-index

    11 publications

    2K citations

  7. Massachusetts Institute of Technology

    Cambridge, United States

    7 h-index

    13 publications

    699 citations

  8. Chinese University of Hong Kong

    Hong Kong, Hong Kong

    6 h-index

    32 publications

    1K citations

1–8 of 181

Venues

  1. arXiv (Cornell University)

    Repository · 42 publications · 4.2K citations

    21

    h-index

  2. Interspeech 2022

    Conference · 20 publications · 1.2K citations

    17

    h-index

  3. 16

    h-index

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

    TASLP · 11 publications · 977 citations

    10

    h-index

  5. 2022 IEEE Spoken Language Technology Workshop (SLT)

    Conference · 8 publications · 224 citations

    8

    h-index

1–5