Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement
This work addresses speech enhancement for noisy environments by integrating audio-visual cues, though it is incremental as it builds on existing embedding-aware methods.
The paper tackled the problem of improving speech enhancement by correlating subword articulation with lip shapes, resulting in a multi-modal framework that significantly outperformed visual-only and audio-only systems in speech quality and intelligibility on the TCD-TIMIT corpus with simulated noises.
In this paper, we propose a visual embedding approach to improving embedding aware speech enhancement (EASE) by synchronizing visual lip frames at the phone and place of articulation levels. We first extract visual embedding from lip frames using a pre-trained phone or articulation place recognizer for visual-only EASE (VEASE). Next, we extract audio-visual embedding from noisy speech and lip videos in an information intersection manner, utilizing a complementarity of audio and visual features for multi-modal EASE (MEASE). Experiments on the TCD-TIMIT corpus corrupted by simulated additive noises show that our proposed subword based VEASE approach is more effective than conventional embedding at the word level. Moreover, visual embedding at the articulation place level, leveraging upon a high correlation between place of articulation and lip shapes, shows an even better performance than that at the phone level. Finally the proposed MEASE framework, incorporating both audio and visual embedding, yields significantly better speech quality and intelligibility than those obtained with the best visual-only and audio-only EASE systems.