Multimodal Attention Fusion for Target Speaker Extraction

TL;DR

This paper introduces a novel attention-based fusion mechanism for audio-visual target speaker extraction, enhancing robustness to clue corruption and demonstrating improved performance on simulated and real data.

Contribution

It proposes a new attention mechanism for multimodal fusion that effectively assesses clue reliability, advancing audio-visual speaker extraction in realistic scenarios.

Findings

Improved SDR by 1.0 dB on simulated data.

Successful application on real recorded mixtures.

Enhanced robustness to visual clue corruption.

Abstract

Target speaker extraction, which aims at extracting a target speaker's voice from a mixture of voices using audio, visual or locational clues, has received much interest. Recently an audio-visual target speaker extraction has been proposed that extracts target speech by using complementary audio and visual clues. Although audio-visual target speaker extraction offers a more stable performance than single modality methods for simulated data, its adaptation towards realistic situations has not been fully explored as well as evaluations on real recorded mixtures. One of the major issues to handle realistic situations is how to make the system robust to clue corruption because in real recordings both clues may not be equally reliable, e.g. visual clues may be affected by occlusions. In this work, we propose a novel attention mechanism for multi-modal fusion and its training methods that enable to effectively capture the reliability of the clues and weight the more reliable ones. Our proposals improve signal to distortion ratio (SDR) by 1.0 dB over conventional fusion mechanisms on simulated data. Moreover, we also record an audio-visual dataset of simultaneous speech with realistic visual clue corruption and show that audio-visual target speaker extraction with our proposals successfully work on real data.