This book constitutes the thoroughly refereed post-proceedings of the Third International Workshop on Machine Learning for Multimodal Interaction, MLMI 2006, held in Bethesda, MD, USA, in May 2006. The papers are organized in topical sections on multimodal processing, image and video processing, HCI and applications, discourse and dialogue, speech and audio processing, and NIST meeting recognition evaluation.Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers Steve Renals, Samy Bengio, Jonathan Fiskus. Table 2. Test set frequencies of the DA types under reference conditions (Ref), STT conditions based on manual segments (STT ... Astraining oftheLMsunder STT conditionsslightly decreased the performance ofthis approach the DA-specific LMs wereanbsp;...
|Title||:||Machine Learning for Multimodal Interaction|
|Author||:||Steve Renals, Samy Bengio, Jonathan Fiskus|
|Publisher||:||Springer Science & Business Media - 2006-12-22|