Machine Learning for Multimodal Interaction

by Renals, Steve; Bengio, Samy; Fiskus, Jonathan

• ISBN13: 9783540692676
• ISBN10: 3540692673
• Format: Paperback
• Copyright: 2006-06-30
• Publisher: Springer Verlag

Summary

This book constitutes the thoroughly refereed post-proceedings of the Third International Workshop on Machine Learning for Multimodal Interaction, MLMI 2006, held in Bethseda, MD, USA, in May 2006. The 39 revised full papers presented together with 1 invited paper were carefully selected during two rounds of reviewing and revision. 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.

Table of Contents

Model-based, multimodal interaction in document browsing	p. 1
The NIST meeting room corpus 2 phase 1	p. 13
Audio-visual processing in meetings : seven questions and current AMI answers	p. 24
A multimodal analysis of floor control in meetings	p. 36
Combining user modeling and machine learning to predict users' multimodal integration patterns	p. 50
Using audio, visual, and lexical features in a multi-modal virtual meeting director	p. 63
A study on visual focus of attention recognition from head pose in a meeting room	p. 75
Multi-person tracking in meetings : a comparative study	p. 88
Gaussian mixture models for CHASM signature verification	p. 102
Kalman tracking with target feedback on adaptive background learning	p. 114
Da Vinci's Mona Lisa : a modern look at a timeless classic	p. 123
The connector service-predicting availability in mobile contexts	p. 129
Multimodal input for meeting browsing and retrieval interfaces : preliminary findings	p. 142
Gesture features for coreference resolution	p. 154
Syntactic chunking across different corpora	p. 166
Multistream recognition of dialogue acts in meetings	p. 178
Text based dialog act classification for multiparty meetings	p. 190
Detecting action items in multi-party meetings : annotation and initial experiments	p. 200
Overlap in meetings : ASR effects and analysis by dialog factors, speakers, and collection site	p. 212
A speaker localization system for lecture room environment	p. 225
Robust speech activity detection in interactive smart-room environments	p. 236
Automatic cluster complexity and quantity selection : towards robust speaker diarization	p. 248
Speaker diarization for multi-microphone meetings using only between-channel differences	p. 257
Warped and warped-twice MVDR spectral estimation with and without filterbanks	p. 265
Robust heteroscedastic linear discriminant analysis and LCRC posterior features in meeting data recognition	p. 275
Juicer : a weighted finite-state transducer speech decoder	p. 285
Speech-to-speech translation services for the olympic games 2008	p. 297
The rich transcription 2006 spring meeting recognition evaluation	p. 309
The IBM RT06s evaluation system for speech activity detection in CHIL seminars	p. 323
A lightweight speech detection system for perceptive environments	p. 336
Robust speaker diarization for meetings : ICSI RT06S meetings evaluation system	p. 346
Technical improvements of the E-HMM based speaker diarization system for meeting records	p. 359
The AMI speaker diarization system for NIST RT06s meeting data	p. 371
The 2006 Athens information technology speech activity detection and speaker diarization systems	p. 385
Speaker diarization : from broadcast news to lectures	p. 396
The ISL RT-06S speech-to-text system	p. 407
The AMI meeting transcription system : progress and performance	p. 419
The IBM rich transcription spring 2006 speech-to-text system for lecture meetings	p. 432
The ICSI-SRI spring 2006 meeting recognition system	p. 444
The LIMSI RT06s lecture transcription system	p. 457
Table of Contents provided by Blackwell. All Rights Reserved.