Once-for-All Sequence Compression for Self-Supervised Speech Models

no code implementations • 4 Nov 2022 • Hsuan-Jui Chen, Yen Meng, Hung-Yi Lee

The sequence length along the time axis is often the dominant factor of the computation in speech processing.

On Compressing Sequences for Self-Supervised Speech Models

no code implementations • 13 Oct 2022 • Yen Meng, Hsuan-Jui Chen, Jiatong Shi, Shinji Watanabe, Paola Garcia, Hung-Yi Lee, Hao Tang

Subsampling while training self-supervised models not only improves the overall performance on downstream tasks under certain frame rates, but also brings significant speed-up in inference.

Self-Supervised Learning

SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities

1 code implementation • ACL 2022 • Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-wen Yang, Shuyan Dong, Andy T. Liu, Cheng-I Jeff Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-Yi Lee

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.

Self-Supervised Learning Transfer Learning

DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering

1 code implementation • 9 Mar 2022 • Guan-Ting Lin, Yung-Sung Chuang, Ho-Lam Chung, Shu-wen Yang, Hsuan-Jui Chen, Shuyan Dong, Shang-Wen Li, Abdelrahman Mohamed, Hung-Yi Lee, Lin-shan Lee

We empirically showed that DUAL yields results comparable to those obtained by cascading ASR and text QA model and robust to real-world data.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2