← authors · overview

• Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
  2023 · 45 citations
• The Interspeech 2025 Speech Accessibility Project Challenge
  2025 · 7 citations
• CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR
  2024
• Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model
  2023
• Identify Speakers in Cocktail Parties with End-to-End Attention
  2020
• Biased Self-supervised learning for ASR
  2022
• Augmenting text for spoken language understanding with Large Language Models
  2023
• Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech
  2024