Technical Program

Unless otherwise specified, events will be held in the Molly Pitcher
Ballroom.

Sunday, Oct 21
--------------
16:30		Registration
18:30		Reception (Navasink Room)
21:00		Free time/sleep

Monday, Oct 22
--------------
 7:00		Registration
 8:00		Breakfast (Southampton Room)
 9:00 		Welcome 
 9:30 		Invited talk: Elizabeth Shriberg, Andreas Stolcke, SRI International
		"Prosody Modeling for Automatic Speech Understanding: An
		Overview of Recent Research at SRI'"
10:30 		Break (Southampton Room)
11:00		Panel Discussion: "Strategic Directions for Prosody Research"
12:00		Lunch (Southampton Room)
13:30		Poster Session
 		- "Duration and pauses as phrasal and boundary 
		   marking indicators in speech", 
		   L. Yang, ATR
		- "Eliminating downstep in prosodic labeling of 
		   American English",
		   A Dainora, U. Chicago
 		- "A prosodically labeled database of spontaneous speech",
		  Mari Ostendorf, Izhak Shafran, Stefanie Shattuck-Hufnagel,
		  Lesley Carmichael, Bill Byrne, MIT and John's Hopkins U.
		- "The Relation Between Stress Accent and Vocalic Identity
		   in Spontaneous American English Discourse"
		   Steven Greenberg, Shawn Chang, Leah Hitchcock, ICSI
		- "Using information on lexical stress for utterance
		   verification",
		   Gies Bouwman and  Lou Boves, U. Nijmegen
		- "Quantitative analysis of F0-induced variations of
		   cepstrum coefficients",
		   Nobuaki Minematsu, Keiichi Tsuda, Keikichi Hirose, U. Tokyo
		- "Modeling Pronunciation Variation in Conversational
         	   Speech using Syntax and Discourse"
		   Rebecca Bates, Mari Ostendorf,  U. Washington
15:30		Break
16:00		Talk Session
	16:00	"Duration features in prosodic classification: why
		 normalization comes second and what they really encode",
		Anton Batliner, Elmar Noeth, Jan Buckow, Richard Huber,
		Volker Warnke, Heinrich Niemann, Erlang U. 	
 	16:30	"Spectral Emphasis as an Additional Source of Information
		in Accent Detection" 
		Mattias Heldner, CTT/KTH
 	17:00	"Prosody and phonetic variability: lessons learned from
		 acoustic model clustering",
		Izhak Shafran, Mari Ostendorf, Richard Wright, U. Washington
17:30		Free time
18:30		Dinner (Navasink Room)
20:00		Boaster Poster Session (Navasink Room)
22:00		End of Day 1

Tuesday, Oct 23
---------------
 8:00		Breakfast (Southampton Room)
 9:00		Invited talk: A. Batliner, Erlangen University
		"Whence and whither prosody in automatic speech understanding:
		a case study"
10:00		Break (Southampton Room)
10:30 		Talk Session
	10:30	"The use of prosody in Japanese dependency structure
		 analysis",
		Kazuhiko Ozeki, Kazuyuki Takagi, Hajime Kubota, UEC Japan
 	11:00	"Use of prosodic speech characteristics for automated
		 detection of alcohol intoxication",
		Michael Levit, Richard Huber, Anton Batliner, Elmar Noeth,
		AT&T and Erlangen U.
	11:30	"Can Prosody Aid the Automatic Processing of Multi-Party
		Meeting? Evidence from Predicting Puntuation, Disfluencies,
		and Overlapping Speech",
	        Elizabeth Shriberg, Andreas Stolcke, Don Baron, SRI
12:00		Lunch (Southampton Room)
14:00		Poster Session
		- "Implications of prosody modeling for prosody recognition",
		  Chilin Shih, Greg Kochanski, Eric Fosler-Lussier,
		  Melody Chan, Jia-Hong Yuan, Bell labs
		- "Temporal features for broadcast news segmentation",
		  Michael T. Johnson and Leah H. Jamieson, Marquette U.
		- "Prosodic correlates of directly reported speech: 
		   evidence from conversational speech",
		  Wouter Jansen, Michelle L. Gregory, Jason M. Brenier,
		  U. Colorado
		- "Prosody pattern recognition and identification of
		   utterance intention in Japanese spontaneous speech",
		  Akira Kurematsu, Mitsuhiro Hosoki, Yasuo Morimoto, 
		  U. Electro-communications
		- "Recognition of accent and intonation types of Japanese
		   using F0 parameters related to human pitch perception",
		  Carlos Toshinori Ishi, Nobuaki Minematsu, Keikichi Hirose,
		  U. Tokyo
		- "Pausing in Dialogues and Read Speech in Swedish: Speakers'
		  Production and Listeners' Interpretation"
		  Beata Megyesi, Sofia Gustafson-Capkova, KTH
		- "Incorporation of prosodic module for large vocabulary
		   continuous speech recognition",
		   Shi-wook Lee, Keikichi Hirose, Nobuaki Minematsu, U. Tokyo
16:00		Break (Southampton Room)
16:30		Talk Session: Confidence and Error Detection
	16:30	"Detecting misrecognitions and corrections in spoken
		 dialogue from predicted `aware' sites",
		Julia Hirschberg, Diane Litman, Marc Swerts, AT&T and IPO
	17:00	"Prosodic scoring of recognition output in the Jupiter
		 domain",
		Chao Wang, Stephanie Seneff, MIT
	17:30	"Disfluency Detection: Classifying repeated words as planned
		or unplanned",
		Cynthia V. Girand, Allen Bell, U. Colorado
18:00		Free Time
19:00		Dinner (Oyster Point Hotel, Terrace Room)
21:00		End of Day 2

Wednesday, Oct 24
-----------------
 8:00		Breakfast (Southampton Room)
 9:00		Talk Session
	 9:00	"The Role of Prosody in a Voicemail Summarization System",
		Konstantinos Koumpis, Steve Renals, Sheffield U.
	 9:30	"Punctuation annotation using statistical prosody models",
		Heidi Christensen, Yoshihiko Gotoh, Steve Renals, Sheffield U.
	10:00	"Continuous Speech Recognition of Japanese Using Prosodic Word
		Boundaries Detected by Mora Transition Modeling of Fundamental
		Frequency Contours"
		Keikichi Hirose, Nobuaki Minematsu, Yohei Hashimoto,
		Koji Iwano, U. Tokyo

10:30		Break (Southampton Room)
11:00		Talk Session
	11:00	"Prosodic Shape and Expressive Meaning: The Expression and
		Recognition of Emotions In Spontaneous Speech"
		Li-chiung Yang, CREST/ATR
	11:30	"Using prosodic features to characterize off-talk in
		 human-computer interaction",
		Rolf Siepmann, Anton Batliner, Daniela Oppermann, U. Munich
12:00		End of the workshop