SUPERB: Speech processing Universal PERformance Benchmark
Journal
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Journal Volume
4
Pages
3161-3165
Date Issued
2021
Author(s)
Yang S.-W
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. Copyright ? 2021 ISCA.
Subjects
Benchmark
Evaluation
Model generalization
Representation learning
Self-supervised learning
Speech
Benchmarking
Learning algorithms
Natural language processing systems
Speech communication
Supervised learning
Large volumes
Performance
Shared model
State of the art
Unlabeled data
Speech processing
SDGs
Type
conference paper