SUPERB @ SLT 2022: Challenge On Generalization And Efficiency Of Self-supervised Speech Representation Learning
2022 · Tzu-Hsun Feng, Annie Dong, Ching-Feng Yeh, et al.
Abstract
We present the SUPERB challenge at SLT 2022, which aims at learning self-supervised speech representation for better performance, generalization, and efficiency. The challenge builds upon the SUPERB benchmark and implements metrics to measure the computation requirements of self-supervised learning (SSL) representation and to evaluate its generalizability and performance across the diverse SUPERB tasks. The SUPERB benchmark provides comprehensive coverage of popular speech processing tasks, from speech and speaker recognition to audio generation and semantic understanding. As SSL has gained interest in the speech community and showed promising outcomes, we envision the challenge to uplevel the impact of SSL techniques by motivating more practical designs of techniques beyond task performance. We summarize the results of 14 submitted models in this paper. We also discuss the main findings from those submissions and the future directions of SSL research.
Authors
(none)
Tags
Stats
Related papers
- ML-SUPERB: Multilingual Speech Universal Performance Benchmark (2023)12.47
- SUPERB-SG: Enhanced Speech Processing Universal Performance Benchmark For Semantic And Generative Capabilities (2022)13.34
- Characterizing The Adversarial Vulnerability Of Speech Self-supervised Learning (2021)4.52
- ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, And Datasets (2024)4.52
- Findings Of The 2023 ML-SUPERB Challenge: Pre-training And Evaluation Over More Languages And Beyond (2023)0.00
- Unispeech-sat: Universal Speech Representation Learning With Speaker Aware Pre-training (2021)0.00
- Lebenchmark: A Reproducible Framework For Assessing Self-supervised Representation Learning From Speech (2021)11.39
- Investigating Self-supervised Learning For Speech Enhancement And Separation (2022)13.44