Machine Learning for Multimodal Interaction

by Renals, Steve; Bengio, Samy

• ISBN13: 9783540325499
• ISBN10: 3540325492
• Format: Paperback
• Copyright: 2006-03-15
• Publisher: Springer-Verlag New York Inc

Summary

This book constitutes the thoroughly refereed post-proceedings of the Second International Workshop on Machine Learning for Multimodal Interaction, MLMI 2005, held in Edinburgh, UK in July 2005. The 38 revised full papers presented together with 2 invited papers were carefully selected during two rounds of reviewing and revision. The papers are organized in topical sections on multimodal processing, HCI and applications, discourse and dialogue, emotion, visual processing, speech and audio processing, and NIST meeting recognition evaluation.

Table of Contents

Gesture, gaze, and ground	p. 1
Toward adaptive information fusion in multimodal systems	p. 15
The AMI meeting corpus : a pre-announcement	p. 28
VACE multimodal meeting corpus	p. 40
Multimodal integration for meeting group action segmentation and recognition	p. 52
Detection and resolution of references to meeting documents	p. 64
Dominance detection in meetings using easily obtainable features	p. 76
Can chimeric persons be used in multimodal biometric authentication experiments?	p. 87
Analysing meeting records : an ethnographic study and technological implications	p. 101
Browsing multimedia archives through intra- and multimodal cross-documents links	p. 114
The "FAME" interactive space	p. 126
Development of peripheral feedback to support lectures	p. 138
Real-time feedback on nonverbal behaviour to enhance social dynamics in small group meetings	p. 150
A multimodal discourse ontology for meeting understanding	p. 162
Generic dialogue modeling for multi-application dialogue systems	p. 174
Toward joint segmentation and classification of dialog acts in multiparty meetings	p. 187
Developing a consistent view on emotion-oriented computing	p. 194
Multimodal authoring tool for populating a database of emotional reactive animations	p. 206
A testing methodology for face recognition algorithms	p. 218
Estimating the lecturer's head pose in seminar scenarios - a multi-view approach	p. 230
Foreground regions extraction and characterization towards real-time object tracking	p. 241
Projective Kalman filter : multiocular tracking of 3D locations towards scene understanding	p. 250
Least squares filtering of speech signals for robust ASR	p. 262
A variable-scale piecewise stationary spectral analysis technique applied to ASR	p. 274
Accent classification for speech recognition	p. 285
Hierarchical multi-stream posterior based speech recognition system	p. 294
Variational bayesian methods for audio indexing	p. 307
Microphone array driven speech recognition : influence of localization on the word error rate	p. 320
Automatic speech recognition and speech activity detection in the CHIL smart room	p. 332
The development of the AMI system for the transcription of speech in meetings	p. 344
Improving the performance of acoustic event classification by selecting and combining information sources using the fuzzy integral	p. 357
The rich transcription 2005 spring meeting recognition evaluation	p. 369
Linguistic resources for meeting speech recognition	p. 390
Robust speaker segmentation for meetings : the ICSI-SRI spring 2005 diarization system	p. 402
Speech activity detection on multichannels of meeting recordings	p. 415
NIST RT'05S evaluation : pre-processing techniques and speaker diarization on multiple microphone meetings	p. 428
The TNO speaker diarization system for NIST RT05s meeting data	p. 440
The 2005 AMI system for the transcription of speech in meetings	p. 450
Further progress in meeting recognition : the ICSI-SRI spring 2005 speech-to-text evaluation system	p. 463
Speaker localization in CHIL lectures : evaluation criteria and results	p. 476
Table of Contents provided by Blackwell. All Rights Reserved.