News from the AASP-TC

by Shoji Makino (AASP-TC Chair)

The Audio and Acoustic Signal Processing (AASP) Technical Committee promotes the advancement of technologies and applications in audio and acoustic signal processing and enhances interaction with similar organizations within IEEE and throughout the world. The AASP TC had its annual TC meeting on May 30, in Vancouver, Canada, where the International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2013 was held. We had 39 attendees. New EDICS unified for Transactions on Audio, Speech and Language Processing, ICASSP, and Signal Processing Letters was proposed by the EDICS Subcommittee chaired by Sharon Gannot, discussed, and approved.

New TC members are being sought for a three-year term, beginning January 1, 2014. We are calling for nominations of high-profile audio and acoustic signal processing researchers, who are willing to actively participate in TC activities, including paper reviews. More information can be found at the TC website. Affiliate Members are always welcome to sign up here.

Honors

The AASP TC had the following successful honors from IEEE.

1. Walter Kellermann has been elected as a member of the IEEE SPS BoG (Board of Governors).
2. Best Paper Award: Tuomas Virtanen, “Monaural Sound Source Separation by Nonnegative Matrix Factorization with Temporal Continuity and Sparse Criteria,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, no. 3, Mar. 2007.
3. Young Author Best Paper Award: Ngoc Q. K. Duong, Emmanuel Vincent and Rémi Gribonval, “Under-Determined Reverberant Audio Source Separation Using a Full-Rank Spatial Covariance Model,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 18, no. 7, Sept. 2010.

Conferences and Workshops

The AASP TC members, associate members, and affiliate members (reviewers) worked hard reviewing papers submitted to ICASSP 2013 held in May, in Vancouver, Canada. Malcolm Slaney, the Review Subcommittee Chair, had spent lots of time on review coordination of 348 submissions in a short time. Michael Brandstein, Simon Doclo, Tomas Gänsler, Jean-Marc Jot , Shoji Makino, Tomohiro Nakatani, Gäel Richard, Hiroshi Sawada, Paris Smagradis, and Akihiko (Ken) Sugiyama helped Malcolm assign reviewers as area chairs who are responsible for their fields of expertise. The number of submissions to the AASP area was increased by 23% compared to last year and marked a record high, demonstrating that AASP is a popular and growing area.

The AASP Technical Committee’s flagship workshop is the Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA). This is a bi-annual event held in odd years in October at Mohonk Mountain House in New Paltz, New York and is intended to stimulate discussions among those working in the AASP area with beautiful autumn leaves. The next WASPAA will be held on October 20-23, 2013, chaired by Sharon Gannot and Emanuel Habets.

The AASP TC is also deeply involved in HSCMA, Joint Workshop on Hands-Free Speech Communication and Microphone Arrays, which is held once every three years. The next HSCMA will be held in Nancy, France, on May 12-14, 2014, chaired by Emmanuel Vincent, in conjunction with ICASSP 2014 and REVERB challenge.

Many members of the AASP TC are deeply involved in the International Workshop on Acoustic Signal Enhancement (IWAENC). IWAENC is held bi-annually in even years, usually in and around the month of September. The next IWAENC will be held in French Riviera, France, on September 9-11, 2014, chaired by Dirk Slock and Christophe Beaugeant.

AASP Challenges

The AASP TC started a new activity, AASP Challenges directed by Patrick Naylor, Chair of AASP TC’s Challenges Subcommittee. It is to introduce a sequence of ‘challenges’ in order to encourage research and development with comparable and repeatable results, and to stimulate new ground‐breaking approaches to specific problems in our technical scope.

“2nd CHiME Speech Separation and Recognition Challenge” follows its previous activities held in 2011. It was a bigger and wider collaboration supported by AASP, SLP, and MLSP TCs. The new challenge extended the difficulty along two independent tracks: a larger vocabulary size and a more realistic mixing process, under the same setting. Organizers were Emmanuel Vincent, Jon Barker, et al. The whole results were made public at a post-ICASSP'13 Workshop in Vancouver on June 1, 2013.

“Detection and Classification of Acoustic Scenes and Events (D-CASE)” is to develop systems that achieve comparable performance to that of human auditory system with the help of computational auditory scene analysis (CASA). This challenge is organized by Mark Plumbley, et al. Results will be presented at a special session in WASPAA 2013; participants are invited to present a poster at the special session. Also, authors of novel work are encouraged to submit their work as a regular paper at WASPAA 2013.

“Reverberant Voice Enhancement and Recognition Benchmark (REVERB)” challenge aims at bringing together researchers from a broad range of disciplines to discuss novel and established approaches to handle reverberant speech. The approaches consist of reverberant speech signal processing, including both single- and multi-channel de-reverberation techniques, and automatic speech recognition (ASR) techniques robust to reverberation. The challenge provides an opportunity to the researchers in the field to carry out comprehensive evaluation of their methods based on a common database and evaluation metrics. Results will be presented at a Workshop on May 10, 2014, in conjunction with ICASSP 2014 and HSCMA 2014.

Job opportunities

A job market page has been popular with many visitors in the AASP TC Jobs Opportunities website. If there is any information about job openings, please direct it to the AASP webmaster, Patrick Naylor.