Two novel visual voice activity detectors based on appearance models and retinal filtering

A Aubrey, B Rivet, Y Hicks, L Girin… - 2007 15th European …, 2007 - ieeexplore.ieee.org
In this paper we present two novel methods for visual voice activity detection (V-VAD) which
exploit the bimodality of speech (ie the coherence between speaker's lips and the resulting …

Robust visual speakingness detection using bi-level HMM

P Tiawongsombat, MH Jeong, JS Yun, BJ You… - Pattern Recognition, 2012 - Elsevier
Visual voice activity detection (V-VAD) plays an important role in both HCI and HRI, affecting
both the conversation strategy and sync between humans and robots/computers. The typical …

[KNIHA][B] Exploiting the bimodality of speech in the cocktail party problem

AJ Aubrey - 2008 - search.proquest.com
The cocktail party problem is one of following a conversation in a crowded room where there
are many competing sound sources, such as the voices of other speakers or music. To …

Study of video assisted BSS for convolutive mixtures

A Aubrey, Y Hicks, S Sanei… - 2006 IEEE 12th Digital …, 2006 - ieeexplore.ieee.org
In this paper we present an overview of recent research in the area of audio-visual blind
source separation (BSS), together with new results of our work that highlight the advantage …