Technical Program

MLSP-L3: Learning in Speech and Audio

Session Type: Lecture
Time: Wednesday, May 29, 10:30 - 12:30
Location: Room 119/120
Session Chair: Paris Smaragdis, University of Illinois at Urbana-Champaign
 
MLSP-L3.1: RANDOM FEATURES FOR KERNEL DEEP CONVEX NETWORK
         Po-Sen Huang; University of Illinois at Urbana-Champaign
         Li Deng; Microsoft Research
         Mark Hasegawa-Johnson; University of Illinois at Urbana-Champaign
         Xiaodong He; Microsoft Corporation
 
MLSP-L3.2: DIRECT PRODUCT BASED DEEP BELIEF NETWORKS FOR AUTOMATIC SPEECH RECOGNITION
         Petr Fousek; IBM Research
         Steven Rennie; IBM Research
         Pierre Dognin; IBM Research
         Vaibhava Goel; IBM Research
 
MLSP-L3.3: DEEP STACKING NETWORKS FOR INFORMATION RETRIEVAL
         Li Deng; Microsoft Research
         Xiaodong He; Microsoft Research
         Jianfeng Gao; Microsoft Research
 
MLSP-L3.4: NON-NEGATIVE DYNAMICAL SYSTEM WITH APPLICATION TO SPEECH AND AUDIO
         Cédric Févotte; Centre National de la Recherche Scientifique (CNRS)
         Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL)
         John R. Hershey; Mitsubishi Electric Research Laboratories (MERL)
 
MLSP-L3.5: BAYESIAN SEMI-SUPERVISED AUDIO EVENT TRANSCRIPTION BASED ON MARKOV INDIAN BUFFET PROCESS
         Yasunori Ohishi; NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
         Daichi Mochihashi; The Institute of Statistical Mathematics
         Tomoko Matsui; The Institute of Statistical Mathematics
         Masahiro Nakano; NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
         Hirokazu Kameoka; NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
         Tomonori Izumitani; NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
         Kunio Kashino; NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation
 
MLSP-L3.6: TOWARDS A UNIVERSAL REPRESENTATION FOR AUDIO INFORMATION RETRIEVAL AND ANALYSIS
         Bjørn Sand Jensen; Technical University of Denmark
         Rasmus Troelsgaard; Technical University of Denmark
         Jan Larsen; Technical University of Denmark
         Lars Kai Hansen; Technical University of Denmark