AI Paper Atlas

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

VoViT: Low Latency Graph-Based Audio-Visual Voice Separation Transformer

Juan F. Montesinos, Venkatesh S. Kadandale, Gloria Haro

ECCV 2022 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 18 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 lead voice enhancer stage 2 (r=1) (ablation)10-block AV ST-transformer · Voxceleb2 wild testSDR: 9.68 -> 10.03Improved
add lead voice enhancer stage 2 (r=1) (ablation)10-block AV ST-transformer · Voxceleb2 wild testSIR: 15.75 -> 18.18Improved
run enhancer twice (r=2) instead of once (ablation)VoViT · Voxceleb2 wild testSDR: 10.03 -> 9.78Hurt
run enhancer twice (r=2) instead of once (ablation)VoViT · Voxceleb2 wild testSIR: 18.18 -> 19.09Improved
use larger Visual Voice U-Net instead of Y-Net U-Net as enhancer (ablation)VoViT · Voxceleb2 wild testSDR: 10.03 -> 10.05No clear effect
use 18-block instead of 10-block single-stage transformer (ablation)VoViT-s1 · Voxceleb2 wild testSDR: 9.68 -> 9.27Hurt
feed audio-visual signal to encoder only instead of video to encoder and audio to decoder (ablation)transformer · Acappella unseen-unheardSDR: 8.64 -> 10.63Improved
feed audio-visual signal only instead of also giving clean audio to decoder (ablation)transformer · Acappella unseen-unheardSDR: 9.98 -> 10.63Improved
replace Y-Net with AV ST-transformerVoViT · Acappella unseen-unheardSDR: 6.41 -> 10.63Improved
replace Visual Voice with VoViTVoViT · Voxceleb2 wild testSIR: 16.11 -> 18.18Improved
replace Visual Voice with VoViTVoViT · Voxceleb2 wild testSDR: 9.92 -> 10.03No clear effect
train on speech instead of singing voiceVoViT-s1 (4 blocks) · Acappella English two-singer mixturesSDR: 14.85 -> 3.89Hurt

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