Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention

TL;DR

This paper introduces SEANet, a novel audio-visual speaker extraction framework that employs a reverse selective auditory attention mechanism to suppress noise and interference, achieving state-of-the-art results across multiple datasets.

Contribution

The paper proposes a new selective auditory attention mechanism and a framework called SEANet that effectively suppresses interference in audio-visual speaker extraction tasks.

Findings

SEANet outperforms baseline methods on five datasets.

The proposed method achieves state-of-the-art results.

SEANet effectively suppresses noise and interference.

Abstract

Audio-visual target speaker extraction (AV-TSE) aims to extract the specific person's speech from the audio mixture given auxiliary visual cues. Previous methods usually search for the target voice through speech-lip synchronization. However, this strategy mainly focuses on the existence of target speech, while ignoring the variations of the noise characteristics, i.e., interference speaker and the background noise. That may result in extracting noisy signals from the incorrect sound source in challenging acoustic situations. To this end, we propose a novel selective auditory attention mechanism, which can suppress interference speakers and non-speech signals to avoid incorrect speaker extraction. By estimating and utilizing the undesired noisy signal through this mechanism, we design an AV-TSE framework named Subtraction-and-ExtrAction network (SEANet) to suppress the noisy signals. We conduct abundant experiments by re-implementing three popular AV-TSE methods as the baselines and involving nine metrics for evaluation. The experimental results show that our proposed SEANet achieves state-of-the-art results and performs well for all five datasets. The code can be found in: https://github.com/TaoRuijie/SEANet.git