4 papers
CoFi-Lite: Pushing the Limits of Ultra-Lightweight Speech Enhancement
Leyan Yang, Dahan Wang, Xiaobin Rong +2
Ultra-lightweight models are essential for the deployment of deep learning-based speech enhancement algorithms on edge devices. Although recent approaches have achieved a certain b…
HALO: Half-Frame-Rate Adaptive Learnable Operator for Lightweight STFT-Based Speech Enhancement
Jiadong Zhao, Dahan Wang, Yu Sun +5
STFT-based speech enhancement typically adopts overlapping analysis frames. While overlap is essential for stable STFT processing, it makes adjacent frames highly correlated, causi…
UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search
Xiaobin Rong, Leyan Yang, Dahan Wang +4
Lightweight models are essential for real-time speech enhancement applications. In recent years, there has been a growing trend toward developing increasingly compact models for sp…
VoCodec: An Efficient Lightweight Low-Bitrate Speech Codec
Leyan Yang, Ronghui Hu, Yang Xu +1
Recent advancements in end-to-end neural speech codecs enable compressing audio at extremely low bitrates while maintaining high-fidelity reconstruction. Meanwhile, low computation…