The paper introduces CF-AVSS, a two‑stage audio‑visual speech separation framework that first generates coarse estimates using a synchronized visual‑stream SPAV‑TFGridNet, then refines these estimates with a TFGridNet‑based target‑speaker refinement network. The final output is a fusion of coarse and refined estimates calibrated on a development set. In the ISCSLP 2026 Real‑World AVSE Challenge, the system tied for first place on Track 1 and ranked second on Track 2, achieving the lowest character error rates of 12.31 % and 14.79 % respectively.
By Longjie Luo, Zhongshu Hou, Yuepeng Li, Gang Yang, Shidong Shang, Fan Zhou
arXiv:2608. 09288v1 Announce Type: cross Abstract: Audio-visual speech enhancement under real-world conditions remains challenging due to unreliable visual inputs and the lack of large-scale training data with realistic acoustic conditions.
By Wei Zhou, Wanyi Ning, Yinshang Guo, Qianxiao Fang, Haitao Qian, Yingpeng Li
arXiv:2609.30631v1 Announce Type: cross
Abstract: Online audio-visual target-speaker extraction aims to remove competing voices while preserving speech quality and bounding lookahead. Existing extrac...
By Rayhan Rashed, Senja Filipi, Ross Cutler
arXiv:2606. 23712v1 Announce Type: cross Abstract: Audio-visual speech enhancement (AVSE) exploits visual cues such as lip movements to recover speech in noisy environments.
By Colombe Mboungou (MULTISPEECH), Mostafa Sadeghi (MULTISPEECH), Jean-Eudes Ayilo (MULTISPEECH), Romain Serizel (MULTISPEECH)
arXiv:2602. 01394v2 Announce Type: replace-cross Abstract: This paper addresses the challenge of audio-visual single-microphone speech separation and enhancement in the presence of real-world environmental noise.
By Yochai Yemini, Yoav Ellinson, Rami Ben-Ari, Sharon Gannot, Ethan Fetaya
arXiv:2606. 06559v1 Announce Type: cross Abstract: Full-duplex spoken dialogue models allow voice agents to listen and speak concurrently, enabling natural interaction with real-time overlap.
By Tao Zhong, Jiajun Deng, Nikita Kuzmin, Yinke Zhu, Tianxiang Cao, Tristan Tsoi, Zhili Tan, Simon Lui, Xunying Liu
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:2609.10366v1 Announce Type: cross
Abstract: While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true...
By Rishabh Jain, Naomi Harte
The paper introduces AV-STE, a modular streaming audio‑visual front‑end that enhances corrupted semantic speech tokens using noisy audio and lip video before they reach a frozen speech LLM. By preserving the downstream dialogue model’s pretrained conversational abilities, AV‑STE improves response coherence from 1.42 to 1.91 in same‑dataset speaker interference scenarios while maintaining turn‑taking behavior. These gains also transfer to out‑of‑domain Seamless Interaction.
By Bella Godiva, Yeonju Kim, Yong Man Ro
The paper addresses challenges in extracting target and multiple speakers from real conversational speech, noting that real conversations contain more silence and enrolment samples that differ from the target speech. It introduces a new loss function that reduces the impact of excess silence during training, yielding improvements in STOI (from 0.55 to 0.60) and frequency‑weighted segmental SNR (from 4.35 to 5.12). The study also investigates how mismatches between enrolment and target speech affect performance.
By Robert Sutherland, Stefan Goetze, Jon Barker
arXiv:2607. 08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable.
By Wanyi Ning, Wei Zhou, Yingpeng Li, Yinshang Guo, Haitao Qian, Yiming Cheng
VM-ARRAYDPS introduces virtual microphones with higher signal‑to‑noise ratios to augment a limited physical microphone array, providing additional multi‑channel consistency constraints for blind speech separation. By leveraging a pretrained speech diffusion model and posterior sampling, the method improves upon the existing ArrayDPS approach. Experiments on 2‑speaker and 3‑speaker datasets show significant performance gains, and ablation studies reveal the impact of virtual microphone count and consistency weighting.
By Jingqi Sun, Haozhan Tang, Shulin He, Zhong-Qiu Wang