[SAPA logo] [ISCA logo]
ISCA Tutorial and Research Workshop on
Statistical And Perceptual Audition
SAPA 2010

Saturday 25 September 2010, Makuhari, Japan
* Home
* Aims
* People
* Dates
* Program
* Register
* SAPA2008
* SAPA2006
* SAPA2004
* SAPA Workshops

Technical Program

The workshop will be held in Conference Center Room 302.

Click on each title to retrieve the corresponding paper.

0945-1000Welcome and introduction
Morning Session: Features and Representation
Chair: Masataka Goto
1000-1030 Supervised vs. Unsupervised Learning of Spectro Temporal Speech Features (pp. 1-6)
Martin Heckmann, Honda Research Institute Europe GmbH
1030-1100 Musical instrument identification based on harmonic temporal timbre features (pp. 7-12)
Jun Wu, Yu Kitano, Takuya Nishimoto, Nobutaka Ono, & Shigeki Sagayama, University of Tokyo
1100-1130 Multiple-F0 Estimation of Piano Sounds Exploiting Spectral Structure and Temporal Evolution (pp. 13-18)
Emmanouil Benetos & Simon Dixon, Queen Mary University of London
1130-1300 lunch
Midday session: Source Separation
Chair: Bhiksha Raj
1300-1330 Distant microphone speech recognition in a noisy indoor environment: combining soft missing data and speech fragment decoding (pp. 19-24)
Ning Ma, Jon Barker, Heidi Christensen, & Phil Green, University of Sheffield
1330-1400 Online Speech Source Separation in Meeting Scene with Time-Varying Weights of Noise Covariance Matrices (pp. 25-30)
Masahito Togami & Koichi Hori, Department of Aeronautics and Astoronautics, School of Engineering, The University of Tokyo, Japan
1400-1430 Informed Source Separation of Orchestra and Soloist Using Masking and Unmasking (pp. 31-36)
Yushen Han & Christopher Raphael, School of Informatics and Computing, Indiana University Bloomington
1430-1500 break
Afternoon session: Statistics and Learning
Chair: Shigeki Sagayama
1500-1530 Detection of polyphonic music note onsets by application of the Bayesian Theory of Surprise (pp. 37-42)
Piotr Holonowicz & Perfecto Herrera, Music Technology Group, Departament of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain
1530-1600 A Statistical Model of Speech F0 Contours (pp. 43-48)
Hirokazu Kameoka, Jonathan Le Roux, & Yasunori Ohishi, NTT
1600-1630 Machine Learning for Learning How the Brain Recognizes Speech and Language (pp. 49-54)
Janet M. Baker, Saras Institute; Alexander M. Chan, Dept. of Neurology, Massachusetts General Hospital and Harvard-MIT Division of Health, Sciece, and Technology, Medical Engineering and Medical Physics; Ksenija Marinkovic, Dept. of Radiology, Univ. of California, San Diego; Eric Halgren, Dept. of Radiology, Univ. of California, San Diego; Sydney S. Cash, Dept. of Neurology, Massachusetts General Hospital
1630-1700 break
1700-1730 Discussion & conclusions
1800 dinner (TBA)

Valid HTML 4.01! Dan Ellis <dpwe@ee.columbia.edu>
Last updated: Thu Sep 23 08:49:08 AM EDT 2010