2 papers
cs.SD2024
Novel-View Acoustic Synthesis from 3D Reconstructed Rooms
Byeongjoo Ahn, Karren Yang, Brian Hamilton +5
We investigate the benefit of combining blind audio recordings with 3D scene information for novel-view acoustic synthesis. Given audio recordings from 2-4 microphones and the 3D g…
cs.LG2024
Hypernetworks for Personalizing ASR to Atypical Speech
Max Müller-Eberstein, Dianna Yee, Karren Yang +2
Parameter-efficient fine-tuning (PEFT) for personalizing automatic speech recognition (ASR) has recently shown promise for adapting general population models to atypical speech. Ho…