Ebook: Machine Learning for Multimodal Interaction: Third International Workshop, MLMI 2006, Bethesda, MD, USA, May 1-4, 2006, Revised Selected Papers

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 39 revised full papers presented together with one 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.

---

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 39 revised full papers presented together with one 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.

Content:
Front Matter....Pages -
Model-Based, Multimodal Interaction in Document Browsing....Pages 1-12
The NIST Meeting Room Corpus 2 Phase 1....Pages 13-23
Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers....Pages 24-35
A Multimodal Analysis of Floor Control in Meetings....Pages 36-49
Combining User Modeling and Machine Learning to Predict Users’ Multimodal Integration Patterns....Pages 50-62
Using Audio, Visual, and Lexical Features in a Multi-modal Virtual Meeting Director....Pages 63-74
A Study on Visual Focus of Attention Recognition from Head Pose in a Meeting Room....Pages 75-87
Multi-person Tracking in Meetings: A Comparative Study....Pages 88-101
Gaussian Mixture Models for CHASM Signature Verification....Pages 102-113
Kalman Tracking with Target Feedback on Adaptive Background Learning....Pages 114-122
Da Vinci’s Mona Lisa....Pages 123-128
The Connector Service-Predicting Availability in Mobile Contexts....Pages 129-141
Multimodal Input for Meeting Browsing and Retrieval Interfaces: Preliminary Findings....Pages 142-153
Gesture Features for Coreference Resolution....Pages 154-165
Syntactic Chunking Across Different Corpora....Pages 166-177
Multistream Recognition of Dialogue Acts in Meetings....Pages 178-189
Text Based Dialog Act Classification for Multiparty Meetings....Pages 190-199
Detecting Action Items in Multi-party Meetings: Annotation and Initial Experiments....Pages 200-211
Overlap in Meetings: ASR Effects and Analysis by Dialog Factors, Speakers, and Collection Site....Pages 212-224
A Speaker Localization System for Lecture Room Environment....Pages 225-235
Robust Speech Activity Detection in Interactive Smart-Room Environments....Pages 236-247
Automatic Cluster Complexity and Quantity Selection: Towards Robust Speaker Diarization....Pages 248-256
Speaker Diarization for Multi-microphone Meetings Using Only Between-Channel Differences....Pages 257-264
Warped and Warped-Twice MVDR Spectral Estimation With and Without Filterbanks....Pages 265-274
Robust Heteroscedastic Linear Discriminant Analysis and LCRC Posterior Features in Meeting Data Recognition....Pages 275-284
Juicer: A Weighted Finite-State Transducer Speech Decoder....Pages 285-296
Speech-to-Speech Translation Services for the Olympic Games 2008....Pages 297-308
The Rich Transcription 2006 Spring Meeting Recognition Evaluation....Pages 309-322
The IBM RT06s Evaluation System for Speech Activity Detection in CHIL Seminars....Pages 323-335
A Lightweight Speech Detection System for Perceptive Environments....Pages 336-345
Robust Speaker Diarization for Meetings: ICSI RT06S Meetings Evaluation System....Pages 346-358
Technical Improvements of the E-HMM Based Speaker Diarization System for Meeting Records....Pages 359-370
The AMI Speaker Diarization System for NIST RT06s Meeting Data....Pages 371-384
The 2006 Athens Information Technology Speech Activity Detection and Speaker Diarization Systems....Pages 385-395
Speaker Diarization: From Broadcast News to Lectures....Pages 396-406
The ISL RT-06S Speech-to-Text System....Pages 407-418
The AMI Meeting Transcription System: Progress and Performance....Pages 419-431
The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings....Pages 432-443
The ICSI-SRI Spring 2006 Meeting Recognition System....Pages 444-456
The LIMSI RT06s Lecture Transcription System....Pages 457-468
Back Matter....Pages -

---

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 39 revised full papers presented together with one 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.

Content:
Front Matter....Pages -
Model-Based, Multimodal Interaction in Document Browsing....Pages 1-12
The NIST Meeting Room Corpus 2 Phase 1....Pages 13-23
Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers....Pages 24-35
A Multimodal Analysis of Floor Control in Meetings....Pages 36-49
Combining User Modeling and Machine Learning to Predict Users’ Multimodal Integration Patterns....Pages 50-62
Using Audio, Visual, and Lexical Features in a Multi-modal Virtual Meeting Director....Pages 63-74
A Study on Visual Focus of Attention Recognition from Head Pose in a Meeting Room....Pages 75-87
Multi-person Tracking in Meetings: A Comparative Study....Pages 88-101
Gaussian Mixture Models for CHASM Signature Verification....Pages 102-113
Kalman Tracking with Target Feedback on Adaptive Background Learning....Pages 114-122
Da Vinci’s Mona Lisa....Pages 123-128
The Connector Service-Predicting Availability in Mobile Contexts....Pages 129-141
Multimodal Input for Meeting Browsing and Retrieval Interfaces: Preliminary Findings....Pages 142-153
Gesture Features for Coreference Resolution....Pages 154-165
Syntactic Chunking Across Different Corpora....Pages 166-177
Multistream Recognition of Dialogue Acts in Meetings....Pages 178-189
Text Based Dialog Act Classification for Multiparty Meetings....Pages 190-199
Detecting Action Items in Multi-party Meetings: Annotation and Initial Experiments....Pages 200-211
Overlap in Meetings: ASR Effects and Analysis by Dialog Factors, Speakers, and Collection Site....Pages 212-224
A Speaker Localization System for Lecture Room Environment....Pages 225-235
Robust Speech Activity Detection in Interactive Smart-Room Environments....Pages 236-247
Automatic Cluster Complexity and Quantity Selection: Towards Robust Speaker Diarization....Pages 248-256
Speaker Diarization for Multi-microphone Meetings Using Only Between-Channel Differences....Pages 257-264
Warped and Warped-Twice MVDR Spectral Estimation With and Without Filterbanks....Pages 265-274
Robust Heteroscedastic Linear Discriminant Analysis and LCRC Posterior Features in Meeting Data Recognition....Pages 275-284
Juicer: A Weighted Finite-State Transducer Speech Decoder....Pages 285-296
Speech-to-Speech Translation Services for the Olympic Games 2008....Pages 297-308
The Rich Transcription 2006 Spring Meeting Recognition Evaluation....Pages 309-322
The IBM RT06s Evaluation System for Speech Activity Detection in CHIL Seminars....Pages 323-335
A Lightweight Speech Detection System for Perceptive Environments....Pages 336-345
Robust Speaker Diarization for Meetings: ICSI RT06S Meetings Evaluation System....Pages 346-358
Technical Improvements of the E-HMM Based Speaker Diarization System for Meeting Records....Pages 359-370
The AMI Speaker Diarization System for NIST RT06s Meeting Data....Pages 371-384
The 2006 Athens Information Technology Speech Activity Detection and Speaker Diarization Systems....Pages 385-395
Speaker Diarization: From Broadcast News to Lectures....Pages 396-406
The ISL RT-06S Speech-to-Text System....Pages 407-418
The AMI Meeting Transcription System: Progress and Performance....Pages 419-431
The IBM Rich Transcription Spring 2006 Speech-to-Text System for Lecture Meetings....Pages 432-443
The ICSI-SRI Spring 2006 Meeting Recognition System....Pages 444-456
The LIMSI RT06s Lecture Transcription System....Pages 457-468
Back Matter....Pages -
....