Technical Program

MLSP-L1: Machine Learning for Speech and Audio Processing

Session Type: Lecture
Time: Tuesday, April 21, 16:00 - 18:00
Location: Mezzanine M3
Session Chair: Jen-Tzung Chien, National Chiao Tung University
 
MLSP-L1.1: MULTICHANNEL TRANSIENT ACOUSTIC SIGNAL CLASSIFICATION USING TASK-DRIVEN DICTIONARY WITH JOINT SPARSITY AND BEAMFORMING
         Yang Zhang; University of Illinois at Urbana-Champaign
         Nasser M. Nasrabadi; U.S. Army Research Laboratory
         Mark Hasegawa-Johnson; University of Illinois at Urbana-Champaign
 
MLSP-L1.2: MIXTURES OF LOCAL DICTIONARIES FOR UNSUPERVISED SPEECH ENHANCEMENT
         Minje Kim; University of Illinois at Urbana-Champaign
         Paris Smaragdis; University of Illinois at Urbana-Champaign
 
MLSP-L1.3: SPEECH DEREVERBERATION USING A LEARNED SPEECH MODEL
         Dawen Liang; Columbia University
         Matthew Hoffman; Adobe Research
         Gautham Mysore; Adobe Research
 
MLSP-L1.4: SOURCE SEPARATION WITH SCATTERING NON-NEGATIVE MATRIX FACTORIZATION
         Joan Bruna; New York University
         Pablo Sprechmann; New York University
         Yann Lecun; New York University / Facebook Inc.
 
MLSP-L1.5: AN ONLINE EM ALGORITHM IN HIDDEN (SEMI-)MARKOV MODELS FOR AUDIO SEGMENTATION AND CLUSTERING
         Alberto Bietti; INRIA, Ircam
         Francis Bach; INRIA, ENS
         Arshia Cont; INRIA, Ircam
 
MLSP-L1.6: REDUNDANCY ANALYSIS OF BEHAVIORAL CODING FOR COUPLES THERAPY AND IMPROVED ESTIMATION OF BEHAVIOR FROM NOISY ANNOTATIONS
         Md Nasir; University of Southern California
         Brian Baucom; University of Utah
         Panayiotis Georgiou; University of Southern California
         Shrikanth S. Narayanan; University of Southern California