AI Paper Atlas

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

An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits

Kai Li, Fenghua Xie, Hang Chen, Kexin Yuan, Xiaolin Hu

TPAMI 2024 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 32 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 visual subnetwork (AV instead of audio-only) (ablation)CTCNet · LRS2-2MixSDRi (dB): 10.1 -> 13.5Improved
add thalamic subnetwork fusion instead of direct AV fusion (CCNet) (ablation)CTCNet · LRS2-2MixSDRi (dB): 10.9 -> 13.5Improved
fuse AV at all layers instead of top layer only (CACNet) (ablation)CTCNet · LRS2-2MixSDRi (dB): 10.2 -> 13.5Improved
add fusion across layers within unimodal subnetworks (ablation)CTCNet · LRS2-2MixSDRi (dB): 13.1 -> 13.5Improved
scale DFTNet to match CTCNet parameters (ablation)DFTNet · LRS2-2MixSDRi (dB): 13.1 -> 13.1No clear effect
add lip-reading pre-training (ablation)CTCNet · LRS2-2MixSDRi (dB): 4.5 -> 13.5Improved
increase auditory cycles m from 1 to 21 (ablation)CTCNet · LRS2-2MixSDRi (dB): 11.8 -> 14.9Improved
use sum instead of concat for AV fusion (ablation)CTCNet n=3 · LRS2-2MixSDRi (dB): 13.6 -> 13.8Improved
increase AV fusion cycles n from 1 to 3 (sum) (ablation)CTCNet · LRS2-2MixSDRi (dB): 13.4 -> 13.8Improved
share weights across time steps in auditory subnetwork (ablation)CTCNet · LRS2-2MixSDRi (dB): 13.3 -> 13.6No clear effect
use CTCNet-Lip rather than MS-TCN lip modelCTCNet · LRS2-2MixSDRi (dB): 13.9 -> 14.3Improved
apply CTCNet separation before ASRGoogle ASR · LRS2 ASR after separationWER (%): 84.91 -> 24.82Improved

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