activity
20242026
most citedDiscrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing

1 citations · 1 across the 9 of their papers we have counts for

collaborators
Showing eess.ASShow all

1 paper · 1 filter

eess.AS2026

Asymmetric Classifier-Free Guidance for Target-Speaker ASR

Yiwen Guan, Jacob Whitehill

Target-speaker automatic speech recognition (TS-ASR) must identify and transcribe a desired speaker under varying overlap and noise conditions. These changes alter the acoustic evi…