2 papers
eess.AS2025
StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models
Yeona Hong, Hyewon Han, Woo-jin Chung +1
In this paper, we propose StableQuant, a novel adaptive post-training quantization (PTQ) algorithm for widely used speech foundation models (SFMs). While PTQ has been successfully…
cs.SD2024
A cross-talk robust multichannel VAD model for multiparty agent interactions trained using synthetic re-recordings
Hyewon Han, Naveen Kumar
In this work, we propose a novel cross-talk rejection framework for a multi-channel multi-talker setup for a live multiparty interactive show. Our far-field audio setup is required…