Shu-wen Yang

PhD student@National Taiwan University·OpenReview

研究方向

self-supervised learning for speech · speech foundation models · benchmarking and evaluation · open source software · audio and speech processing · deep learning

5.5

ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction

ICLR 2026Poster

一作

7.0

Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks

ICLR 2025Poster

三作

6.6

IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling

ICML 2025Poster

二作

4.8

Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction

合作者 (20)