We address the problem of robust lip tracking, visual speech feature extraction, and sensor integration for audio-visual speech recognition applications. An appearance based model of the articulators, which represents linguistically important features, is learned from example images and is used to locate, track, and recover visual speech information. We tackle the problem of joint temporal modelling of the acoustic and visual speech signals by applying Multi-Stream hidden Markov models. This approach allows the use of different temporal topologies and levels of stream integration and hence enables to model temporal dependencies more accurately. The system has been evaluated for a continuously spoken digit recognition task of 37 subjects.