AI Paper Atlas

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

Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face Video

Minsu Kim, Joanna Hong, Se Jin Park, Yong Man Ro

ICCV 2021 · Vision-language and multimodal › Cross-modal learning · approach: Audio-visual speech separation · 55 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 recalled audio features via associative bridge to visual lip readingvisual lip reading baseline · LRWword accuracy: 84.14 -> 85.41Improved
add associative bridge memory with best slot count N=112visual lip reading baseline · LRW-1000word accuracy: +5.89%; 50.82Improved
vary number of memory slots (N=88 best) (ablation)proposed bridging · LRWword accuracy: 85.41; +1.27%Improved
use any number of memory slots (ablation)proposed bridging · LRW and LRW-1000word accuracyImproved
use modality-specific memory bridge instead of cross-modal adaptationlip reading · LRWword accuracy: 84.20 -> 85.41Improved
use bridge instead of knowledge distillation from ASR featureslip reading · LRWword accuracy: 84.50 -> 85.41Improved
add recalled audio context to speech reconstruction (speaker-dependent)Lip2Wav · GRID speaker-dependentESTOI: 0.535 -> 0.579Improved
add recalled audio context to speech reconstruction (speaker-independent)Lip2Wav · GRID speaker-independentSTOI: 0.565 -> 0.600Improved
vary memory slots in speech reconstruction (N=150 best) (ablation)proposed bridging · GRID speaker-dependentSTOI/ESTOI/PESQ: 0.738, 0.579, 1.984Improved
swap Griffin-Lim for WaveNet vocoderproposed speech reconstruction · GRID human evaluationintelligibility MOS: 3.56 -> 4.27Improved
proposed vs Lip2Wav on naturalnessspeech reconstruction · GRID human evaluationnaturalness MOS: 2.83 -> 2.93No clear effect

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