International Conference on Auditory-Visual Speech Processing 2008

Tangalooma Wild Dolphin Resort, Moreton Island, Queensland, Australia
September 26-29, 2008

Audio-Visual Voice Command Recognition in Noisy Conditions

Josef Chaloupka, Jan Nouza, Jindrich Zdansky

Laboratory of Computer Speech Processing, Institute of Information Technology and Electronics, Technical University of Liberec, Czech Republic

This paper presents an experiment of audio-visual voice command recognition from small vocabulary in simulated noisy conditions. Electric and electronics devices should be controlled by these voice commands mainly in homes of motor-handicapped people and visual part of speech could improve recognition rate if a noise is relatively strong. Therefore the main aims of this experiment were to find out how visual part of speech can improve resulting recognition rate and if it is possible to use successfully two-stream Hidden Markov Models (HMMs) for audio-visual voice command recognition.

Full Paper

Bibliographic reference.  Chaloupka, Josef / Nouza, Jan / Zdansky, Jindrich (2008): "Audio-visual voice command recognition in noisy conditions", In AVSP-2008, 25-30.