Multimodal signal processing is an important new field that processes signals from a variety of modalities - speech, vision, language, text- derived from one source, which aids human-computer and human-human interaction. The overarching theme of this book is the application of signal processing and statistical machine learning techniques to problems arising in this field. It gives an overview of the field, the capabilities and limitations of current technology, and the technical challenges that must be overcome to realize multimodal interactive systems. As well as state-of-the-art methods in multimodal signal and image modeling and processing, the book gives numerous examples and applications of multimodal interactive systems, including humancomputer and human-human interaction. This is the definitive reference in multimodal signal processing, edited and contributed by the leading experts, for signal processing researchers and graduates, R&D engineers and computer engineers.