Showing 2025Show all
2 papers · 1 filter
cs.SD2025
LABNet: A Lightweight Attentive Beamforming Network for Ad-hoc Multichannel Microphone Invariant Real-Time Speech Enhancement
Haoyin Yan, Jie Zhang, Chengqian Jiang +1
Multichannel speech enhancement (SE) aims to restore clean speech from noisy measurements by leveraging spatiotemporal signal features. In ad-hoc array conditions, microphone invar…
eess.AS2025
A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement
Jie Zhang, Haoyin Yan, Xiaofei Li
It is promising to design a single model that can suppress various distortions and improve speech quality, i.e., universal speech enhancement (USE). Compared to supervised learning…