Technical Program
SP-P4: Acoustic Modeling for Automatic Speech Recognition |
| Session Type: Poster |
| Time: Tuesday, May 28, 15:30 - 17:30 |
| Location: Poster Area D |
| Session Chair: Malcolm Slaney, Microsoft |
| SP-P4.1: EFFECT OF FILTER BANDWIDTH AND SPECTRAL SAMPLING RATE OF ANALYSIS FILTERBANK ON AUTOMATIC PHONEME RECOGNITION |
| Feipeng Li; Johns Hopkins University |
| Hynek Hermansky; Johns Hopkins University |
| SP-P4.2: PROBABILISTIC ASR FEATURE EXTRACTION APPLYING CONTEXT-SENSITIVE CONNECTIONIST TEMPORAL CLASSIFICATION NETWORKS |
| Martin Woellmer; BMW Group |
| Björn Schuller; Technische Universität München |
| Gerhard Rigoll; Technische Universität München |
| SP-P4.3: OPTIMIZED MFCC FEATURE EXTRACTION ON GPU |
| Haofeng Kou; Santa Clara University |
| Weijia Shang; Santa Clara University |
| Ian Lane; Carnegie Mellon University |
| Jike Chong; Carnegie Mellon University |
| SP-P4.4: MULTI-VIEW CCA-BASED ACOUSTIC FEATURES FOR PHONETIC RECOGNITION ACROSS SPEAKERS AND DOMAINS |
| Raman Arora; Toyota Technological Institute at Chicago |
| Karen Livescu; Toyota Technological Institute at Chicago |
| SP-P4.5: PERFORMANCES OF UNSUPERVISED HMM IN ACOUSTIC-TO-ARTICULATORY INVERSION |
| Helene Lachambre; IRIT - University of Toulouse |
| Lionel Koenig; IRIT - University of Toulouse |
| Régine André-Obrecht; IRIT - University of Toulouse |
| SP-P4.6: ARTICULATORY TRAJECTORIES FOR LARGE-VOCABULARY SPEECH RECOGNITION |
| Vikramjit Mitra; SRI International |
| Wen Wang; SRI International |
| Andreas Stolcke; Microsoft Research |
| Hosung Nam; Haskins Laboratories |
| Colleen Richey; SRI International |
| Jiahong Yuan; University of Pennsylvania |
| Mark Liberman; University of Pennsylvania |
| SP-P4.7: DISTINCT TRIPHONE MODELING BY REFERENCE MODEL WEIGHTING |
| Dongpeng Chen; The Hong Kong University of Science and Technology |
| Brian Mak; The Hong Kong University of Science and Technology |
| SP-P4.8: A NEW PHASE-BASED FEATURE REPRESENTATION FOR ROBUST SPEECH RECOGNITION |
| Erfan Loweimi; Amirkabir University of Technology (Tehran Polytechnic) |
| Seyed Mohammad Ahadi; Amirkabir University of Technology (Tehran Polytechnic) |
| Thomas Drugman; Université de Mons |
| SP-P4.9: CHANNEL-MAPPING FOR SPEECH CORPUS RECYCLING |
| Osamu Ichikawa; IBM |
| Steven Rennie; IBM |
| Takashi Fukuda; IBM |
| Masafumi Nishimura; IBM |
| SP-P4.10: AN EVALUATION OF POSTERIOR MODELING TECHNIQUES FOR PHONETIC RECOGNITION |
| Rohit Prabhavalkar; The Ohio State University |
| Tara N. Sainath; IBM T.J. Watson Research Center |
| David Nahamoo; IBM T.J. Watson Research Center |
| Bhuvana Ramabhadran; IBM T.J. Watson Research Center |
| Dimitri Kanevsky; IBM T.J. Watson Research Center |
| SP-P4.11: ACCENT ADAPTATION USING SUBSPACE GAUSSIAN MIXTURE MODELS |
| Petr Motlicek; Idiap Research Institute |
| Philip N. Garner; Idiap Research Institute |
| Namhoon Kim; Samsung Electronics Co. Ltd |
| Jeongmi Cho; Samsung Electronics Co. Ltd |
| SP-P4.12: SEMI-SUPERVISED ACCENT DETECTION AND MODELING |
| Shilei Zhang; IBM Research |
| Yong Qin; IBM Research |
| SP-P4.13: TONE RECOGNITION FOR CONTINUOUS ACCENTED MANDARIN CHINESE |
| Jiang Wu; SUNY-Binghamton |
| Stephen A. Zahorian; SUNY-Binghamton |
| Hongbing Hu; SUNY-Binghamton |
| SP-P4.14: SUBMODULAR FEATURE SELECTION FOR HIGH-DIMENSIONAL ACOUSTIC SCORE SPACES |
| Yuzong Liu; University of Washington |
| Kai Wei; University of Washington |
| Katrin Kirchhoff; University of Washington |
| Yisong Song; University of Washington |
| Jeff Bilmes; University of Washington |