AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

CogCM: Cognition-Inspired Contextual Modeling for Audio-Visual Speech Enhancement

Feixiang Wang, Shuang Yang, Shiguang Shan, Xilin Chen

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add pre-trained noisy audio-visual semantic context module (SeCMPAV) (ablation)CogCM · LRS3+DNS -15dBSDR: 5.171 -> 6.680Improved
add visual-only semantic module trained from scratch (SeCMV) (ablation)CogCM · LRS3+DNS -15dBSDR: 5.171 -> 5.414Improved
use pre-trained audio-visual module on noisy speech instead of clean-pretrained visual module (ablation)SeCM · LRS3+DNS -15dBSDR: 6.112 -> 6.680Improved
use Bi-Mamba signal context module instead of Conformer (ablation)CogCM (audio-visual) · LRS3+DNS -15dBSDR: 4.656 -> 5.414Improved
use SSGM guidance instead of simple addition fusion (ablation)CogCM with SeCMPAV · LRS3+DNS -15dBSDR: 6.680 -> 7.284Improved
use SSGM instead of addition at small PESQ/STOI scale (ablation)CogCM with SeCMV · LRS3+DNS -5dBSTOI: 0.891 -> 0.892No clear effect
add frequency upsampling and frequency guidance block (visual frequency) (ablation)SSGM · LRS3+DNS -15dBSDR: 6.803 -> 7.284Improved
model time first then frequency instead of parallel or reverse order (ablation)SSGM · LRS3+DNSperformanceImproved
replace DualAVSE with CogCM (average over SNRs)AVSE · LRS3+DNSPESQ: +53.6% over DualAVSEImproved
replace EANet with CogCMAVSE · GRID/TCD-TIMIT + NoiseX-92PESQi: +21.2% PESQi, +35.7% STOIi, +28.7% SI-SDRiImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy