Title | ||
---|---|---|
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities |
Abstract | ||
---|---|---|
Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks. However, the lack of a consistent evaluation methodology is limiting towards a holistic understanding of the efficacy of such models. SUPERB was a step towards introducing a common benchmark to evaluate pre-trained models across various speech tasks. In this paper, we introduce SUPERB-SG, a new benchmark focused on evaluating the semantic and generative capabilities of pre-trained models by increasing task diversity and difficulty over SUPERB. We use a lightweight methodology to test the robustness of representations learned by pre-trained models under shifts in data domain and quality across different types of tasks. It entails freezing pre-trained model parameters, only using simple task-specific trainable heads. The goal is to be inclusive of all researchers, and encourage efficient use of computational resources. We also show that the task diversity of SUPERB-SG coupled with limited task supervision is an effective recipe for evaluating the generalizability of model representation. |
Year | DOI | Venue |
---|---|---|
2022 | 10.18653/v1/2022.acl-long.580 | PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS) |
DocType | Volume | Citations |
Conference | Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) | 2 |
PageRank | References | Authors |
0.35 | 0 | 17 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hsiang-Sheng Tsai | 1 | 2 | 0.35 |
Heng-Jui Chang | 2 | 2 | 0.35 |
Wen-Chin Huang | 3 | 2 | 0.35 |
Zili Huang | 4 | 17 | 5.47 |
Kushal Lakhotia | 5 | 15 | 1.02 |
Shu-wen Yang | 6 | 17 | 1.38 |
Shuyan Dong | 7 | 16 | 2.08 |
T. Liu | 8 | 34 | 9.67 |
Cheng-I Jeff Lai | 9 | 15 | 1.02 |
Jiatong Shi | 10 | 15 | 1.02 |
Xuankai Chang | 11 | 24 | 4.34 |
Phil Hall | 12 | 2 | 0.35 |
Hsuan-Jui Chen | 13 | 2 | 0.69 |
Shang-Wen Li | 14 | 15 | 2.71 |
Shinji Watanabe | 15 | 1158 | 139.38 |
Abdel-rahman Mohamed | 16 | 3772 | 266.13 |
Hung-Yi Lee | 17 | 217 | 45.30 |