DNN driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation

TL;DR

This paper introduces a novel deep neural network model that combines audio and visual cues to improve speech separation, mimicking human selective attention and outperforming audio-only and visual-only methods.

Contribution

The study presents a hybrid DNN architecture integrating LSTM and convolution LSTM for audiovisual mask estimation, enhancing speech separation performance.

Findings

Significant improvement in speech quality and intelligibility over audio-only and visual-only methods.

Effective integration of temporal dynamics of audio and visual features.

Robust performance in both speaker-dependent and independent scenarios.

Abstract

Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on target speaker while filtering out other noises. In this study, we propose a novel deep neural network (DNN) based audiovisual (AV) mask estimation model. The proposed AV mask estimation model contextually integrates the temporal dynamics of both audio and noise-immune visual features for improved mask estimation and speech separation. For optimal AV features extraction and ideal binary mask (IBM) estimation, a hybrid DNN architecture is exploited to leverages the complementary strengths of a stacked long short term memory (LSTM) and convolution LSTM network. The comparative simulation results in terms of speech quality and intelligibility demonstrate significant performance improvement of our proposed AV mask estimation model as compared to audio-only and visual-only mask estimation approaches for both speaker dependent and independent scenarios.