Sound Source Localization is All about Cross-Modal Alignment

TL;DR

This paper emphasizes the importance of cross-modal semantic understanding in sound source localization, proposing a joint alignment task to improve localization accuracy and semantic comprehension in audio-visual scenes.

Contribution

It introduces a novel cross-modal alignment task combined with localization, enhancing semantic understanding and outperforming existing methods in both areas.

Findings

Outperforms state-of-the-art in sound source localization

Achieves superior cross-modal retrieval performance

Demonstrates the importance of semantic understanding in localization

Abstract

Humans can easily perceive the direction of sound sources in a visual scene, termed sound source localization. Recent studies on learning-based sound source localization have mainly explored the problem from a localization perspective. However, prior arts and existing benchmarks do not account for a more important aspect of the problem, cross-modal semantic understanding, which is essential for genuine sound source localization. Cross-modal semantic understanding is important in understanding semantically mismatched audio-visual events, e.g., silent objects, or off-screen sounds. To account for this, we propose a cross-modal alignment task as a joint task with sound source localization to better learn the interaction between audio and visual modalities. Thereby, we achieve high localization performance with strong cross-modal semantic understanding. Our method outperforms the state-of-the-art approaches in both sound source localization and cross-modal retrieval. Our work suggests that jointly tackling both tasks is necessary to conquer genuine sound source localization.