Technical Program

AASP-L3: Source Separation and Speech Enhancement I

Session Type: Lecture
Time: Wednesday, May 15, 08:30 - 10:30
Location: Meeting Room 1
Session Chair: Minje Kim, Indiana University Bloomington
 
AASP-L3.1: DEEP GRIFFIN–LIM ITERATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Yoshiki Masuyama; Waseda University
         Kohei Yatabe; Waseda University
         Yuma Koizumi; NTT Corporation
         Yasuhiro Oikawa; Waseda University
         Noboru Harada; NTT Corporation
 
AASP-L3.2: THE PHASEBOOK: BUILDING COMPLEX MASKS VIA DISCRETE REPRESENTATIONS FOR SOURCE SEPARATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories
         Gordon Wichern; Mitsubishi Electric Research Laboratories
         Shinji Watanabe; Johns Hopkins University
         Andy Sarroff; iZotope
         John R. Hershey; Google Research
 
AASP-L3.3: DEEP LEARNING BASED PHASE RECONSTRUCTION FOR SPEAKER SEPARATION: A TRIGONOMETRIC PERSPECTIVE
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Zhong-Qiu Wang; The Ohio State University
         Ke Tan; The Ohio State University
         DeLiang Wang; The Ohio State University
 
AASP-L3.4: LOW-LATENCY DEEP CLUSTERING FOR SPEECH SEPARATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Shanshan Wang; Tampere University of Technology
         Gaurav Naithani; Tampere University of Technology
         Tuomas Virtanen; Tampere University of Technology
 
AASP-L3.5: UNSUPERVISED DEEP CLUSTERING FOR SOURCE SEPARATION: DIRECT LEARNING FROM MIXTURES USING SPATIAL INFORMATION
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Efthymios Tzinis; University of Illinois at Urbana-Champaign
         Shrikant Venkataramani; University of Illinois at Urbana-Champaign
         Paris Smaragdis; University of Illinois at Urbana-Champaign, Adobe Research
 
AASP-L3.6: SINGLE-CHANNEL SPEECH EXTRACTION USING SPEAKER INVENTORY AND ATTENTION NETWORK
Manuscript Link:  Click here to view manuscript on IEEE Xplore
         Xiong Xiao; Microsoft
         Zhuo Chen; Microsoft
         Takuya Yoshioka; Microsoft
         Hakan Erdogan; Microsoft
         Changliang Liu; Microsoft
         Dimitrios Dimitriadis; Microsoft
         Jasha Droppo; Microsoft
         Yifan Gong; Microsoft