AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tseng, Yuan, Berry, Layne, Chen, Yi-Ting, Chiu, I-Hsiang, Lin, Hsuan-Hao, Liu, Max, Peng, Puyuan, Shih, Yi-Jen, Wang, Hung-Yu, Wu, Haibin, Huang, Po-Yao, Lai, Chun-Mao, Li, Shang-Wen, Harwath, David, Tsao, Yu, Watanabe, Shinji, Mohamed, Abdelrahman, Feng, Chi-Luen, Lee, Hung-yi
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916164978868224
author Tseng, Yuan
Berry, Layne
Chen, Yi-Ting
Chiu, I-Hsiang
Lin, Hsuan-Hao
Liu, Max
Peng, Puyuan
Shih, Yi-Jen
Wang, Hung-Yu
Wu, Haibin
Huang, Po-Yao
Lai, Chun-Mao
Li, Shang-Wen
Harwath, David
Tsao, Yu
Watanabe, Shinji
Mohamed, Abdelrahman
Feng, Chi-Luen
Lee, Hung-yi
author_facet Tseng, Yuan
Berry, Layne
Chen, Yi-Ting
Chiu, I-Hsiang
Lin, Hsuan-Hao
Liu, Max
Peng, Puyuan
Shih, Yi-Jen
Wang, Hung-Yu
Wu, Haibin
Huang, Po-Yao
Lai, Chun-Mao
Li, Shang-Wen
Harwath, David
Tsao, Yu
Watanabe, Shinji
Mohamed, Abdelrahman
Feng, Chi-Luen
Lee, Hung-yi
contents Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization abilities of learned representations are unclear. To this end, we propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations on 7 datasets covering 5 audio-visual tasks in speech and audio processing. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks, emphasizing the need for future study on improving universal model performance. In addition, we show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task. We release our benchmark with evaluation code and a model submission platform to encourage further research in audio-visual learning.
format Preprint
id arxiv_https___arxiv_org_abs_2309_10787
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models
Tseng, Yuan
Berry, Layne
Chen, Yi-Ting
Chiu, I-Hsiang
Lin, Hsuan-Hao
Liu, Max
Peng, Puyuan
Shih, Yi-Jen
Wang, Hung-Yu
Wu, Haibin
Huang, Po-Yao
Lai, Chun-Mao
Li, Shang-Wen
Harwath, David
Tsao, Yu
Watanabe, Shinji
Mohamed, Abdelrahman
Feng, Chi-Luen
Lee, Hung-yi
Audio and Speech Processing
Computer Vision and Pattern Recognition
Multimedia
Sound
Audio-visual representation learning aims to develop systems with human-like perception by utilizing correlation between auditory and visual information. However, current models often focus on a limited set of tasks, and generalization abilities of learned representations are unclear. To this end, we propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations on 7 datasets covering 5 audio-visual tasks in speech and audio processing. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks, emphasizing the need for future study on improving universal model performance. In addition, we show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task. We release our benchmark with evaluation code and a model submission platform to encourage further research in audio-visual learning.
title AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models
topic Audio and Speech Processing
Computer Vision and Pattern Recognition
Multimedia
Sound
url https://arxiv.org/abs/2309.10787