Technical Program

SP-P2: Speech Recognition I

Session Type: Poster
Time: Tuesday, March 22, 13:30 - 15:30
Location: Poster Area I
Session Chair: Hagen Soltau, Google Inc.
 
SP-P2.1: SUPERVISED AND UNSUPERVISED ACTIVE LEARNING FOR AUTOMATIC SPEECH RECOGNITION OF LOW-RESOURCE LANGUAGES
         Ali Raza Syed; The Graduate Center CUNY
         Andrew Rosenberg; The Graduate Center CUNY
         Ellen Kislal; IBM Thomas J. Watson Research Center
 
SP-P2.2: PARALLELIZING WFST SPEECH DECODERS
         Charith Mendis; Massachusetts Institute of Technology
         Jasha Droppo; Microsoft Research
         Saeed Maleki; Microsoft Research
         Madanlal Musuvathi; Microsoft Research
         Todd Mytkowicz; Microsoft Research
         Geoffrey Zweig; Microsoft Research
 
SP-P2.3: ACCELERATING MULTI-USER LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION ON HETEROGENEOUS CPU-GPU PLATFORMS
         Jungsuk Kim; Carnegie Mellon University
         Ian Lane; Carnegie Mellon University
 
SP-P2.4: CHARACTER-LEVEL INCREMENTAL SPEECH RECOGNITION WITH RECURRENT NEURAL NETWORKS
         Kyuyeon Hwang; Seoul National University
         Wonyong Sung; Seoul National University
 
SP-P2.5: AUDIO WORD SIMILARITY FOR CLUSTERING WITH ZERO RESOURCES BASED ON ITERATIVE HMM CLASSIFICATION
         Amélie Royer; ENS Rennes
         Guillaume Gravier; CNRS
         Vincent Claveau; CNRS
 
SP-P2.6: CONVOLUTIONAL NEURAL NETWORK PRE-TRAINED WITH PROJECTION MATRICES ON LINEAR DISCRIMINANT ANALYSIS
         Takashi Fukuda; IBM
         Osamu Ichikawa; IBM
         Ryuki Tachibana; IBM
 
SP-P2.7: ACOUSTIC DATA-DRIVEN PRONUNCIATION LEXICON GENERATION FOR LOGOGRAPHIC LANGUAGES
         Guoguo Chen; Johns Hopkins University
         Daniel Povey; Johns Hopkins University
         Sanjeev Khudanpur; Johns Hopkins University
 

ICASSP 2016 Patrons