Welcome to the 2011 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) on the Big Island of Hawaii (Dec 11th – 15th, 2011). ASRU workshops have been held biannually since 1989; some of the most well-known work in the speech community has debuted at ASRU. This year, we are privileged to host ASRU in Hawaii at the Hilton Waikoloa Resort. The combination of the beautiful venue and the wonderful set of papers promise to be an unforgettable experience for the attendees.
This year, we are trying to enhance the ASRU experience by trying to encourage cross-fertilization of ideas between speech and other related communities. We have keynote speakers from NLP (Jennifer Chu-Carroll), Vision (David Forsyth), Neural Processing (Frank Guenther) and Machine Learning (Yoram Singer). We are hoping each one of these speakers will present ideas that will stimulate discussions that will benefit speech research, and will also take ideas from speech back to their respective areas.
We also have a set of excellent invited talks illustrating many new technologies and applications including speech translation for lectures and speeches (Marcello Federico), improved spoken content retrieval performance using lattices (Lin-Shan Lee), behavioral inference from speech (Shri Narayanan), methods for robust speech recognition across multiple sources of degradation (Mike Seltzer), a machine learning view of speech synthesis (Keiichi Tokuda), and information source integration for speech recognition using segmental conditional random fields (Geoff Zweig).
A total of 234 papers were submitted for the poster sessions and 98 papers were accepted. The review process was managed by the Technical Chairs, Jerome Bellegarda (Apple), Bhuvana Ramabhadran (IBM), Murat Saraclar (Bogazici University) and Dimitra Vergyri (SRI). We would like to thank them for their excellent work and dedication. We also would like to express our gratitude to the volunteer work done by the scientific committee members, the technical reviewers, and the session chairs.
The “Show and Tell” session takes place under the guidance of the chairs Olivier Siohan and Patrick Nguyen of Google. Special thanks go to these chairs as well as to the publication chairs Thomas Hain (Sheffield University) and Kai Yu (Cambridge University), the publicity chair Jason Williams (AT&T Labs) and the local chairs, Victoria Anderson and Suzanne Still of the University of Hawaii. We also thank Eric Fosler-Lussier (Ohio State) for serving as finance chair. Sara Basson (IBM) was instrumental in the initial logistics of choosing a venue and hotel; without her leadership we would have landed somewhere in the Pacific Ocean. We of course thank Billene Mercer and the rest of CMS for their able conference management services. Finally, Andy Aaron and Larry Sansone, who have been associated with the Speech Group at IBM for years, deserve a special set of thanks for handling and managing the nearly-infinite number of details that accompany a major workshop such as ASRU.
The ASRU workshop social, technical events and paper awards would not be possible without the generous contributions of our sponsors: Google, Nuance, Microsoft, IBM Research, Cisco, EML and ISCA.
Speech technology is now touching a previously unheard of number of people thanks to ubiquitous devices such as smartphones, cameras, car systems, and related sensors. The challenge to our community is to increase performance so that the technology really achieves the potential we all dream about. There is a Hawaiian proverb: “Pūpūkahi i holomua” – “Unite to move forward.” Breakthroughs arise not only in our respective labs, but also from the interactions that result when we get our leading researchers together in an immersive venue like ASRU. We hope you enjoy the conference and return home with many new ideas and new friendships.
Mahalo nui loa!
David Nahamoo and Michael Picheny (IBM Research)