Speech, Image, and Language Processing for Human Computer Interaction ─ Multi-Modal Advancements

The first section of this volume surveys user modeling techniques for human-computer interaction (HCI), categorizes HCI architectures according to cognition, and compares interactive cognitive models of the cooperative design environment. The second section collects methods for speech, image, and language processing for multimodal interaction while the final section describes multimodal interfaces. Topics of the 15 papers include digital audio spatialization, Hindi speech recognition from visual cues, multi-finger gesture recognition and classification, HCI for enhanced metasearching, and automatic speech analysis for evaluating speech disorders. Annotation Ac2012 Book News, Inc., Portland, OR (booknews.com)