2022/12/01 by Rahul Sharma, Shrikanth Narayanan, Sharma, Rahul +1 · 2 citations
Arts and Humanities · Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimedia (cs.MM) #Music and Audio Processing #Speech and Audio Processing #Subtitles and Audiovisual Media
paper · pdf · doi:10.48550/arxiv.2212.00539
openalex publication_date 2022/12/01 · openalex created_date 2022/12/13 · openalex updated_date 2026/07/28
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.