activity
20232026
most citedDeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data

15 citations · 23 across the 29 of their papers we have counts for

collaborators
Showing 2023Show all

2 papers · 1 filter

eess.AS2023★ 1 cited

Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision

Chih-Kai Yang, Kuan-Po Huang, Ke-Han Lu +3

This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, o…

eess.AS2023

Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech

Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang +12

Text language models have shown remarkable zero-shot capability in generalizing to unseen tasks when provided with well-formulated instructions. However, existing studies in speech…