An increasing desire amongst speech researchers to share their knowledge in this field led to the first international conference on Speech Prosody held in April 2002 in Aix-en-Provence, France (Speech Prosody 2002, chaired by Daniel Hirst at the Laboratoire Parole et Langage (CNRS), University of Provence). Speech Prosody is organized by SProSIG, the ISCA Special Interest Group on Speech Prosody, which aims to provide information and resources for the support and coordination of this research.

Because of the great success of SP2002, many researchers working in the domain of speech prosody have been looking forward to its sequel. Corresponding to this request, we in Japan agreed to host the second conference in Nara, an ancient capital with a long cultural history.

Currently, two major projects related to prosody are being carried out in Japan: one is “Prosody and Speech Processing,” a large-scale national project supported by a Grant-in-Aid for Scientific Research on Priority Areas from the Ministry of Education, Culture, Sports, Science and Technology of Japan (headed by Keikichi Hirose at the University of Tokyo), and the other is “Expressive Speech Processing” funded by the Japan Science and Technology Agency (headed by Nick Campbell at ATR). Given such a vibrant research base, it is opportune to host the second Speech Prosody conference at this time. The conference highlights issues from the basic sciences and from applications in technology, education, and medicine. Researchers will receive an up-to-date overview of the entire field.

Preparations started immediately after SP2002, and thanks to numerous volunteers, we are now ready to hold SP2004 in late March, when the climate and scenery in Nara are ideal. The conference site, “Big Roof” (the Nara-Ken New Public Hall) is located in the heart of Nara city and many sightseeing locations are within easy walking distance. Visit them and refresh yourselves in-between technical discussions.

Speech prosody covers a huge multidisciplinary area involving academics, scientists, and engineers with various research backgrounds, united by an interest in human communication. Prosodic features play an important role in speech and language research, and the current developments in speech technology call for further interdisciplinary work that builds on this diverse variety of inputs. Corresponding to our call-for-paper announcement, the program committee received close to 200 proposals from various areas of speech prosody and from 30 countries. We selected several important topics and invited leading researchers to present plenary papers in each area. We are very grateful for their support.

Together with the Vice-chair of this conference, Nick Campbell, I thank all the members of the International Advisory Committee, the International Scientific Committee, and the Organizing Committee. Also, I appreciate all the paper authors and attendants of Speech Prosody 2004.

Finally, this conference received financial support from a number of organizations. Without their generosity, the conference may not have happened.

Enjoy your stay in Nara.

Reflecting the wide interest and vigorous activities in this field, we received 180 submissions, from which the Technical Program Committee has accepted 164: 29 papers for oral presentation, and 135 for poster presentation. We are very grateful to all the contributors; without their interest and efforts it would not have been possible to organize an international conference of this quality.

Besides contributed papers, we also invited 12 papers, and organized the sessions as follows. In the Opening Session, three eminent researchers will present lectures: Professor Hiroya Fujisaki on “Information, Prosody, and Modeling - with Emphasis on Tonal Features of Speech,” Professor Ilse Lehiste on “Prosody in Speech and Singing,” and Professor Miyoko Sugito on “50 Years of Studies on Japanese Prosody.” One or two oral sessions will be held each day: Oral-1 “Phonology and Phonetics of Prosody,” Oral-2 “Prosody and Voice Quality,” Oral-3 “Paralinguistic and Nonlinguistic Information and Prosody,” Oral-4 “Control of Prosody for High-quality and Expressive Speech Synthesis,” Oral-5 “Prosody in Speech Recognition, Understanding, and Summarization,” and Oral-6 “Physiology and Pathology of Prosody.” We organized 9 poster sessions: two or three in parallel each day. I would like to add that the distinction between oral papers and poster papers does not reflect the quality of the paper. It is just a matter of topic. Indeed, all sessions contain many high quality papers. As with Speech Prosody 2002, all oral presenters have been offered the opportunity of using poster boards to supplement the short presentation time.

I would like to thank all members of the Scientific Committee for their hard work of reviewing papers in a very tight schedule. My thanks also go to Program Co-Chairs, Professor Yoshinori Sagisaka, and Dr. Kikuo Maekawa for helping me arrange everything. Lastly, I am most grateful to Dr. Bernard Bel, SProSIG Secretary, and Dr. Nobuaki Minematsu, our conference Secretary, for their constant and patient hard work.