Lip-Reading Driven Deep Learning Approach for Speech Enhancement

Abstract

This paper proposes a novel lip-reading driven deep learning framework for speech enhancement. The approach leverages the complementary strengths of both deep learning and analytical acoustic modeling (filtering-based approach) as compared to benchmark approaches that rely only on deep learning. The proposed audio-visual (AV) speech enhancement framework operates at two levels. In the first level, a novel deep learning based lip-reading regression model is employed. In the second level, lip-reading approximated clean-audio features are exploited, using an enhanced, visually-derived Wiener filter (EVWF), for estimating the clean audio power spectrum. Specifically, a stacked long-short-term memory (LSTM) based lip-reading regression model is designed for estimating the clean audio features using only temporal visual features (i.e., lip reading), by considering a range of prior visual frames. For clean speech spectrum estimation, a new filterbank-domain EVWF is formulated, which exploits the estimated speech features. The EVWF is compared with conventional spectral subtraction and log-minimum mean-square error methods using both ideal AV mapping and LSTM driven AV mapping approaches. The potential of the proposed AV speech enhancement framework is evaluated under four different dynamic real-world scenarios [cafe, street junction, public transport, and pedestrian area] at different SNR levels (ranging from low to high SNRs) using benchmark grid and ChiME3 corpora. For objective testing, perceptual evaluation of speech quality is used to evaluate the quality of restored speech. For subjective testing, the standard mean-opinion-score method is used with inferential statistics. Comparative simulation results demonstrate significant lip-reading and speech enhancement improvements in terms of both speech quality and speech intelligibility. Ongoing work is aimed at enhancing the accuracy and generalization capability of the deep learning driven lip-reading model, using contextual integration of AV cues, leading to context-aware, autonomous AV speech enhancement.