Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement

TL;DR

This paper introduces a multi-modal speech enhancement method that uses visual lip cues at subword levels, demonstrating improved speech quality and intelligibility over traditional audio-only or visual-only systems.

Contribution

It proposes a novel visual embedding approach at phoneme and articulation levels, and combines audio-visual features for enhanced speech processing.

Findings

Visual embedding at articulation place level outperforms phone level.

Multi-modal embedding significantly improves speech quality and intelligibility.

Proposed methods outperform conventional word-level embedding approaches.

Abstract

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.