Abstract—This paper presents a new database containing high-definition audio and video recordings in a rather unconstrained video-conferencing-like environment. The database consists of recordings of people sitting around a table in two separate rooms communicating and playing online games with each other. Extensive annotation of head positions, voice activity and word transcription has been performed on the dataset, making it especially useful for evaluating automatic speech-recognition, voice activity detection, speaker localisation, multi-face detection and tracking, and other audio-visual analysis algorithms.

Index Terms—High-definition video-conferencing, multi-face-tracking, multi-modal database, voice-activity detection.

The authors are with the Idiap Research Institute, Rue Marconi 19, 1920Martigny, Switzerland (e-mail: stefan.duffner@idiap.ch,petr.motlicek@idiap.ch, danil.korchagin@idiap.ch)

Cite: Stefan Duffner, Petr Motlicek, and Danil Korchagin, "The TA2 Database – A Multi-Modal Database From Home Entertainment," International Journal of Computer and Electrical Engineering vol. 4, no. 5, pp. 670-673 , 2012.