Tracking the Active Speaker Based on a Joint Audio-Visual Observation Model

Israel Dejene Gebru (1) , Silèye Ba (1) , Georgios Evangelidis (1) , Radu Horaud (1)

1 PERCEPTION - Interpretation and Modelling of Images and Videos

Any multi-party conversation system benefits from speaker diarization, that is, the assignment of speech signals among the participants. We here cast the diarization problem into a tracking formulation whereby the active speaker is detected and tracked over time. A probabilistic tracker exploits the on-image (spatial) coincidence of visual and auditory observations and infers a single latent variable which represents the identity of the active speaker. Both visual and auditory observations are explained by a recently proposed weighted-data mixture model, while several options for the speaking turns dynamics are fulfilled by a multi-case transition model. The modules that translate raw audio and visual data into on-image observations are also described in detail. The performance of the proposed tracker is tested on challenging data-sets that are available from recent contributions which are used as baselines for comparison.

Mots clés: Speaker diarization; Audio-visual fusion; Sound-source localization; Multi-person tracking; Temporal graphical models

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Multimédia [cs.MM]

Israel Dejene Gebru, Silèye Ba, Georgios Evangelidis, Radu Horaud. Tracking the Active Speaker Based on a Joint Audio-Visual Observation Model. ICCV Workshop on 3D Reconstruction and Understanding with Video and Sound , Dec 2015, Santiago, Chile. pp.702 - 708, ⟨10.1109/ICCVW.2015.96⟩. ⟨hal-01220956⟩