Recent advances in speech separation (SS) have led to compact front-end models with small parameter sizes, yet their high computational cost remains a major barrier for deployment on edge devices. To address this, we propose TF-MoE, a sparse Mixture-of-Experts (MoE) framework that enhances model capacity with almost no increase in inference cost.
arXiv:2606. 09677v1 Announce Type: cross Abstract: While discriminative models for multi-channel speech separation excel in reference-based metrics, they often exhibit suboptimal human listening quality.
By Dohwan Kim, Jung-Woo Choi
arXiv:2604. 01832v1 Announce Type: cross Abstract: We introduce GAP-URGENet, a generative-predictive fusion framework developed for Track 1 of the ICASSP 2026 URGENT Challenge.
By Xiaobin Rong, Yushi Wang, Zheng Wang, Jing Lu
arXiv:2609.07226v1 Announce Type: cross
Abstract: This paper proposes a general framework for stable and effective iterative audio separation with mixture consistency by extending source separation m...
By Yukara Ikemiya, WeiHsiang Liao, Yuki Mitsufuji
arXiv:2606. 01909v1 Announce Type: cross Abstract: We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder.
By Louis Mouchon
arXiv:2608. 12715v1 Announce Type: cross Abstract: Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics, and Schr\"odinger Bridges (SB) shorten transport from noise to clean speech but leave inference cost only loosely tied to training.
By Zhengyi Lu, Aswini Sivakumar, Jie Hu, Yao Qiang