AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection
This addresses the problem of constrained algorithm evaluation and comparisons for researchers and developers in video analysis, though it is incremental as it builds on existing dataset efforts.
The paper tackles the lack of a large, labeled audio-visual dataset for active speaker detection by introducing AVA-ActiveSpeaker, which contains 3.65 million labeled frames (38.5 hours) of face tracks and audio, and presents a new audio-visual method with analyzed performance.
Active speaker detection is an important component in video analysis algorithms for applications such as speaker diarization, video re-targeting for meetings, speech enhancement, and human-robot interaction. The absence of a large, carefully labeled audio-visual dataset for this task has constrained algorithm evaluations with respect to data diversity, environments, and accuracy. This has made comparisons and improvements difficult. In this paper, we present the AVA Active Speaker detection dataset (AVA-ActiveSpeaker) that will be released publicly to facilitate algorithm development and enable comparisons. The dataset contains temporally labeled face tracks in video, where each face instance is labeled as speaking or not, and whether the speech is audible. This dataset contains about 3.65 million human labeled frames or about 38.5 hours of face tracks, and the corresponding audio. We also present a new audio-visual approach for active speaker detection, and analyze its performance, demonstrating both its strength and the contributions of the dataset.