Authors IndexSessionTechnical programAttendees

 

 



Dear Friends and Colleagues,



On behalf of the workshop committee, welcome to the 2001 IEEE workshop on Automatic Speech Recognition and Understanding (ASRU). This is the seventh of a series of biannual workshops sponsored by the IEEE Signal Processing Society, and previously held at Arden House (1989, 1991), Snowbird (1993, 1995), Santa Barbara (1997) and Keystone (1999).


This time, the workshop takes place on December 9-13, 2001 in Madonna di Campiglio (Italy), marking the first time ASRU is held outside the United States. Madonna di Campiglio, considered one of the best ski resorts in Italy, is located in the heart of the Brenta Dolomites near the town of Trento. The workshop is hosted at the Historical Golf Hotel, built at the end of the 19th century by the Habsburg Emperor of Austria Franz-Josef, and recently restored respecting the atmosphere and original style. See Empress Sissi's favorite ballroom and enjoy the breathtaking scenery.


During the last decade, speech interface technology has advanced to a point that it is no longer considered academic research only. The increasing interest in bringing speech recognition technology to real-world field applications suggests the organization of a workshop where students and researchers from academia and industry are stimulated to collaborate and discuss on problems of common interest. This year the technical program comprises three keynotes, six sessions, three panel discussions and a demo-exhibition night.


It is a privilege to have three stimulating keynotes given by distinguished experts: The symbiosis of DSP and speech recognition or an outsider's view of the inside   by Jim Kaiser of Duke University (USA), VoiceXML and Natural Language Processing   by Jim Larson of Intel (USA), and Brancusi, neo-plasticism and the art of designing speech-recognition applications   by Christopher Kotelly of SpeechWorks (USA).


There will be six oral sessions on very exciting topics: ASR Robustness (Feature Extraction, Acoustic Modeling and Adaptation), Wireless ASR, Distributed Speech Recognition and Hands Free Interaction, Large Vocabulary (Language Modeling and Speech Understanding), Dialogue Systems (Voice Agents, Applications, and Field Trials), Audio-video Information Retrieval and Digital Archives, Multilingual and Speech-to-Speech Translation.   We will also have three panel sessions entitled Impact of Infrastructure (wireless communication systems, devices, etc) and Multimodality when applying ASR to Hand-held Devices, Driving force in the technology for Spoken Language Dialogue Systems, and Portability of ASR Technology to New Languages:Multilinguality Issues and Speech/Text Resources.   We would like to thank all of the invited speakers and panelists, for contributing to the success of these sessions and panels, providing their experience and vision about the future of this technology.


Special thanks go to our session chairs, Alex Potamianos (Bell Labs - Lucent Technologies, USA), Sadaoki Furui (Tokyo Institute of Technology, Japan), Giuseppe Riccardi (AT&T Labs Research, USA), Roberto Pieraccini (SpeechWorks, USA), Jean Luc Gauvain (LIMSI-CNRS, France) and Enrique Vidal (Univ. Politecnica of Valencia, Spain), for contributing in inviting speakers and coordinating the scientific review activity. We are also grateful to Hsiao Wuen Hon (Microsoft Research, USA.), Christel Sorin (France Telecom, USA), and Jimmy Kunzmann (IBM Speech Systems, Germany), for the organization of the three panel discussions. Without their precious help, those high quality sessions and panel discussions would have not been possible.


This year, 125 papers (not including invited papers) were submitted; a 25% increase over ASRU99. Due to space limitations only 96 papers could be accepted. These 96 papers will be presented during six poster sessions. We would like to show our appreciation to the 44 scientific reviewers who conducted a fair and rapid evaluation, with each paper being reviewed by at least two reviewers.


The demo-exhibition night on Tuesday is sponsored by Loquendo, Microsoft, Nuance, and Sony. Demonstrations by those companies, as well as universities and other research centers, will showcase the advanced level offered by present speech recognition applications.


We would like to thank every member of the organizing committee for the support and advice they gave us during the whole preparation of ASRU2001. We thank Roberto Pieraccini, Alex Potamianos and Giuseppe Riccardi for their thorough work in delineating the technical program, a marathon filled with numerous intercontinental conference calls. We also want to thank Jean-Luc Gauvain for publicizing this workshop, Isabel Trancoso for attracting co-sponsors and organizing the demo night, Sadaoki Furui for publicizing the workshop in the Far East, Gianni Lazzari, Morena Carli, Letizia Pasini, Piergiorgio Svaizer, Alessandro Tuccio and all the other colleagues at ITC for the incredible amount of logistics work they have done to make this workshop a reality.


We would also like to thank ISCA for having allocated five student grants, among authors of accepted papers.


Finally, special thanks go to APT Madonna di Campiglio   for their financial contribution to the Gala Dinner, Telecom Italia   for providing free Internet access during the whole workshop, and the IEEE Signal Processing Society   for having supported and encouraged the organization of ASRU in a site so far from those of previous ASRUs.


The Golf Hotel and its surroundings is a very suggestive and quiet place to organize a workshop. Besides full immersion in speech recognition, ASRU2001 will feature a Welcome Reception on Sunday night, a Habsburgic dinner on Monday, a buffet dinner on Tuesday, and a Gala Dinner on Wednesday night. And for those downhill skiing lovers, the famous 3TRE Ski World Cup Night Slalom will take place on Monday only one kilometer away from the Golf Hotel.


We wish you all a wonderful time in Madonna di Campiglio!


Maurizio Omologo and Alex Acero

General Co-Chairs of ASRU 2001

 

P.S. In the wake of the tragic events of September 11th, some companies have restricted travel of their employees and, as a consequence, there have been some cancellations and some delayed registrations. Because of this, the final technical program and final list of attendees were not available in time for the CDROM mastering process. We hope that the contents of this CDROM are as close as possible to the final ones. We also wish that violence and war will be replaced as soon as possible by peace everywhere in the world.