collaborators

7 papers

eess.AS2026

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…

eess.AS2026

PhASE-Flow: Phonetic-Conditioned Acoustic Flow Matching in SSL Representation Domain for Speech Enhancement

Jun Gao, Xiaobin Rong, Yu Sun +2

Flow matching (FM) enables high-fidelity generation, while self-supervised learning (SSL) speech models provide hierarchical representations spanning acoustic and phonetic levels.…

eess.AS2026

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…

eess.AS2026

Rethinking Flow and Diffusion Bridge Models for Speech Enhancement

Dahan Wang, Jun Gao, Tong Lei +4

Flow matching and diffusion bridge models have emerged as leading paradigms in generative speech enhancement, modeling stochastic processes between paired noisy and clean speech si…

eess.AS2026

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…

eess.AS2025

Adaptive Convolution for CNN-based Speech Enhancement Models

Dahan Wang, Xiaobin Rong, Shiruo Sun +3

Deep learning-based speech enhancement methods have significantly improved speech quality and intelligibility. Convolutional neural networks (CNNs) have been proven to be essential…