Papers by Heng-Jui Chang
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities (2022.acl-long)
Copied to clipboard
Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-wen Yang, Shuyan Dong, Andy Liu, Cheng-I Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
| Challenge: | Existing evaluation methods for transfer learning are limited in speech research . authors show that pre-trained models transfer well across multiple tasks . |
| Approach: | They propose a benchmark to evaluate pre-trained models by increasing task diversity and difficulty over SUPERB. |
| Outcome: | The proposed benchmark increases task diversity and difficulty over SUPERB-SG. |
R-Spin: Efficient Speaker and Noise-invariant Representation Learning with Acoustic Pieces (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for speaker and noise-invariant speech representations use unlabeled audio data to pretrain encoders, generating good representations for downstream tasks like automatic speech recognition (ASR) and speaker identification. |
| Approach: | They propose a domain-specific self-supervision method for speaker and noise-invariant speech representations by learning discrete acoustic units with speaker-in-variant clustering. |
| Outcome: | The proposed method reduces computational resources by 12X compared to state-of-the-art methods while outperforming them in severely distorted speech scenarios. |