@inproceedings{c3dc05c30cb444cd9482071f7a11eedb,
title = "SUPERB: Speech processing Universal PERformance Benchmark",
abstract = "Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data. Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL for its preferable re-usability. We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model. Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks. We release SUPERB as a challenge with a leaderboard1 and a benchmark toolkit2 to fuel the research in representation learning and general speech processing.",
keywords = "Benchmark, Evaluation, Model generalization, Representation learning, Self-supervised learning, Speech",
author = "Yang, {Shu Wen} and Chi, {Po Han} and Chuang, {Yung Sung} and Lai, {Cheng I.Jeff} and Kushal Lakhotia and Lin, {Yist Y.} and Liu, {Andy T.} and Jiatong Shi and Xuankai Chang and Lin, {Guan Ting} and Huang, {Tzu Hsien} and Tseng, {Wei Cheng} and Lee, {Ko Tik} and Liu, {Da Rong} and Zili Huang and Shuyan Dong and Li, {Shang Wen} and Shinji Watanabe and Abdelrahman Mohamed and Lee, {Hung Yi}",
note = "Publisher Copyright: Copyright {\textcopyright} 2021 ISCA.; 22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021 ; Conference date: 30-08-2021 Through 03-09-2021",
year = "2021",
doi = "10.21437/Interspeech.2021-1775",
language = "English",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association",
pages = "3161--3165",
booktitle = "22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021",
}