Technical Program

AASP-L5: Source Separation II

Session Type: Lecture
Time: Thursday, March 24, 16:00 - 18:00
Location: Room 3C+3D
Session Chairs: Tao Zhang, Starkey Hearing Technologies and Mads Christensen, Aalborg University
 
AASP-L5.1: DEEP UNFOLDING FOR MULTICHANNEL SOURCE SEPARATION
         Scott Wisdom; University of Washington
         John R. Hershey; Mitsubishi Electric Research Laboratories
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories
         Shinji Watanabe; Mitsubishi Electric Research Laboratories
 
AASP-L5.2: COMMON FATE MODEL FOR UNISON SOURCE SEPARATION
         Fabian-Robert Stöter; International Audio Laboratories Erlangen
         Antoine Liutkus; Inria
         Roland Badeau; Télécom ParisTech
         Bernd Edler; International Audio Laboratories Erlangen
         Paul Magron; Télécom ParisTech
 
AASP-L5.3: A SOURCE/FILTER MODEL WITH ADAPTIVE CONSTRAINTS FOR NMF-BASED SPEECH SEPARATION
         Damien Bouvier; IRCAM
         Nicolas Obin; IRCAM
         Marco Liuni; IRCAM
         Axel Roebel; IRCAM
 
AASP-L5.4: AN INVERSE-GAMMA SOURCE VARIANCE PRIOR WITH FACTORIZED PARAMETERIZATION FOR AUDIO SOURCE SEPARATION
         Dionyssos Kounades-Bastian; Institute Nationale Recherche Informatique Automatique INRIA
         Laurent Girin; Universite Grenoble Alpes
         Xavier Alameda-Pineda; University of Trento
         Sharon Gannot; Bar-Ilan University
         Horaud-Patrice Radu; Institute Nationale Recherche Informatique Automatique INRIA
 
AASP-L5.5: BLIND SPEECH SEPARATION BASED ON COMPLEX SPHERICAL K-MODE CLUSTERING
         Lukas Drude; University of Paderborn
         Christoph Boeddeker; University of Paderborn
         Reinhold Haeb-Umbach; University of Paderborn
 
AASP-L5.6: PHONEME-SPECIFIC SPEECH SEPARATION
         Zhong-Qiu Wang; The Ohio State University
         Yan Zhao; The Ohio State University
         DeLiang Wang; The Ohio State University
 

ICASSP 2016 Patrons