Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection

TL;DR

This paper introduces an unsupervised framework that combines audio-visual activity cues and speaker identity information to improve active speaker detection in videos, addressing limitations of individual methods.

Contribution

It proposes a novel late fusion approach that leverages the complementary strengths of activity-based and identity-based methods for better speaker detection.

Findings

Fusion improves detection accuracy on benchmark datasets.

Combining modalities reduces confusion with non-speech vocal activities.

Unsupervised framework eliminates need for extensive labeled data.

Abstract

Active speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality. The two primary sources of information to derive such a speech-face relationship are i) visual activity and its interaction with the speech signal and ii) co-occurrences of speakers' identities across modalities in the form of face and speech. The two approaches have their limitations: the audio-visual activity models get confused with other frequently occurring vocal activities, such as laughing and chewing, while the speakers' identity-based methods are limited to videos having enough disambiguating information to establish a speech-face association. Since the two approaches are independent, we investigate their complementary nature in this work. We propose a novel unsupervised framework to guide the speakers' cross-modal identity association with the audio-visual activity for active speaker detection. Through experiments on entertainment media videos from two benchmark datasets, the AVA active speaker (movies) and Visual Person Clustering Dataset (TV shows), we show that a simple late fusion of the two approaches enhances the active speaker detection performance.