Technical Program

AASP-L3: Deep Learning for Source Separation and Enhancement I

Session Type: Lecture
Time: Wednesday, March 8, 08:30 - 10:30
Location: Grand Salon 15
Session Chairs: Paris Smaragdis, and Minje Kim, University of Indiana
 
AASP-L3.1: DEEP CLUSTERING AND CONVENTIONAL NETWORKS FOR MUSIC SEPARATION: STRONGER TOGETHER
         Yi Luo; Columbia University
         Zhuo Chen; Columbia University
         John R. Hershey; Mitsubishi Electric Research Laboratories
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories
         Nima Mesgarani; Columbia University
 
AASP-L3.2: DNN-BASED SPEECH MASK ESTIMATION FOR EIGENVECTOR BEAMFORMING
         Lukas Pfeifenberger; TU Graz
         Matthias Zöhrer; TU Graz
         Franz Pernkopf; TU Graz
 
AASP-L3.3: RECURRENT DEEP STACKING NETWORKS FOR SUPERVISED SPEECH SEPARATION
         Zhong-Qiu Wang; The Ohio State University
         DeLiang Wang; The Ohio State University
 
AASP-L3.4: COLLABORATIVE DEEP LEARNING FOR SPEECH ENHANCEMENT: A RUN-TIME MODEL SELECTION METHOD USING AUTOENCODERS
         Minje Kim; Indiana University Bloomington
 
AASP-L3.5: DNN-BASED SOURCE ENHANCEMENT SELF-OPTIMIZED BY REINFORCEMENT LEARNING USING SOUND QUALITY MEASUREMENTS
         Yuma Koizumi; NTT Corporation
         Kenta Niwa; NTT Corporation
         Yusuke Hioka; University of Auckland
         Kazunori Kobayashi; NTT Corporation
         Yoichi Haneda; The University of Electro-Communications
 
AASP-L3.6: A NEURAL NETWORK ALTERNATIVE TO NON-NEGATIVE AUDIO MODELS
         Paris Smaragdis; University of Illinois
         Shrikant Venkataramani; University of Illinois