It is our great pleasure to welcome you to the 16th International Workshop on Acoustic Signal Enhancement (IWAENC) to be held at Hitotsubashi Hall in Tokyo, Japan, on September 17 – 20, 2018. IWAENC was established in 1993, originally as the International Workshop on Acoustic Echo and Noise Control (this is how the abbreviation IWAENC came into use consistently). After that, it grew up to be a wider-scope workshop introducing many state-of-the-art topics, e.g., speech enhancement, multichannel signal processing, source separation, dereverberation, and robot audition. It is the leading workshop in the signal processing community addressing theoretical and technical issues related to acoustic and speech signal acquisition and processing.
A total of 132 papers were submitted and 114 were accepted as high-quality publications and presentations. The four-day program consists of oral and poster presentations including a special session, plenary talks, and demonstrations. Especially in three plenary talks, we cordially invite Prof. Tuomas Virtanen from Tampere University of Technology, Finland, Prof. Masashi Sugiyama from RIKEN CAIP and The University of Tokyo, Japan, and Dr. John Hershey from Google, U.S.A., who are the prominent and world's leading scientists on not only acoustic signal processing but also machine learning. Their talks will cover recent great success of machine learning including deep neural networks in acoustic and speech signal processing, and shape the next-generation directions that are of particular interest to all of the participants. In the special session, we offer the topic on "signal processing for multi-party conversation," which is definitely one of the main applications in the speech enhancement community. Besides the regular and special sessions, this workshop has a close conjunction with "IEEE-AASP Challenge on Acoustic Source Localization and Tracking (LOCATA)" session that many IWAENC participants will be interested in.
There are many people that should be thanked for their hard work, which helped to make this workshop successful. First of all, we would like to thank all the authors and the voluntary reviewers; without them there would be no workshop. Our deepest gratitude is addressed to Nobutaka Ono and Zbynek Koldovsky, who are the Technical Program Chairs, for their wonderful and devoted works to construct the well-organized technical program with high denseness. Also, the organization of whole workshop is always very demanding (but sometimes a pleasant task), which needs an excellent engaged team. We warmly thank all members of Organizing Committee and International Steering Committee for their extraordinary job and constant support to take care of all details including local arrangements. Finally, we are very thankful for the big-hearted financial support from our academic and industry sponsors; here we specially thank the great support from Ichimura Foundation for New Technology as the 45th Ichimura-Gakujutsu Award for our contribution on "blind source separation for high quality speech interface."
This is the second IWAENC held in Japan. In 2003, the first workshop was held at Kyoto, an ancient capital with many historical places. In good contrast to Kyoto, this IWAENC is in Tokyo; Tokyo is the capital city of Japan, which is modern and cosmopolitan, yet rich in cultural heritage. Majestic skyscrapers contrast with the venerable Tokyo Station building and nearby Imperial Palace with its moat and inner gardens, which is a short walk from the workshop venue. Visitors may also take a leisurely pace to enjoy the sights and sounds of Tokyo Bay aboard an old-fashioned Yakatabune houseboat, dinning in traditional style, which will be offered in this workshop's banque.
Above all, we wish all of you to enjoy a nice workshop, fruitful discussions and academic exchange, and excellent stay in Tokyo.
Hiroshi Saruwatari, The University of Tokyo
Shoji Makino, University of Tsukuba
(General Chairs of IWAENC2018)