CVDec 14, 2021

Multi-Modal Perception Attention Network with Self-Supervised Learning for Audio-Visual Speaker Tracking

arXiv:2112.07423v130 citations
Originality Highly original
AI Analysis

This work addresses speaker tracking for applications in noisy or occluded environments, representing a strong specific gain with incremental improvements in multi-modal fusion.

The paper tackled the problem of speaker tracking in complex scenarios by proposing a Multi-modal Perception Tracker (MPT) that fuses audio and visual signals, achieving 98.6% and 78.3% tracking accuracy on standard and occluded datasets.

Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of multi-modal signals remains a challenging issue. In this paper, we propose a novel Multi-modal Perception Tracker (MPT) for speaker tracking using both audio and visual modalities. Specifically, a novel acoustic map based on spatial-temporal Global Coherence Field (stGCF) is first constructed for heterogeneous signal fusion, which employs a camera model to map audio cues to the localization space consistent with the visual cues. Then a multi-modal perception attention network is introduced to derive the perception weights that measure the reliability and effectiveness of intermittent audio and video streams disturbed by noise. Moreover, a unique cross-modal self-supervised learning method is presented to model the confidence of audio and visual observations by leveraging the complementarity and consistency between different modalities. Experimental results show that the proposed MPT achieves 98.6% and 78.3% tracking accuracy on the standard and occluded datasets, respectively, which demonstrates its robustness under adverse conditions and outperforms the current state-of-the-art methods.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes