Technical Program
SP-P1: Acoustic Modeling: Discriminative methods |
| Session Type: Poster |
| Time: Tuesday, May 28, 10:50 - 12:50 |
| Location: Poster Area D |
| Session Chair: Gernot Kubin, Graz University of Technology |
| SP-P1.1: EFFECTIVENESS OF DISCRIMINATIVE TRAINING AND FEATURE TRANSFORMATION FOR REVERBERATED AND NOISY SPEECH |
| Yuuki Tachioka; Mitsubishi Electric |
| Shinji Watanabe; Mitsubishi Electric Research Laboratories (MERL) |
| John R. Hershey; Mitsubishi Electric Research Laboratories (MERL) |
| SP-P1.2: TIED-STATE BASED DISCRIMINATIVE TRAINING OF CONTEXT-EXPANDED REGION-DEPENDENT FEATURE TRANSFORMS FOR LVCSR |
| Zhi-Jie Yan; Microsoft Research Asia |
| Qiang Huo; Microsoft Research Asia |
| Jian Xu; Microsoft Research Asia |
| Yu Zhang; Microsoft Research Asia |
| SP-P1.3: STATE OF THE ART DISCRIMINATIVE TRAINING OF SUBSPACE CONSTRAINED GAUSSIAN MIXTURE MODELS IN BIG TRAINING CORPORA |
| Jing Huang; IBM |
| Peder Olsen; IBM |
| Vaibhava Goel; IBM |
| SP-P1.4: KERNELIZED LOG LINEAR MODELS FOR CONTINUOUS SPEECH RECOGNITION |
| Shi-Xiong Zhang; Cambridge University |
| Mark J.F. Gales; Cambridge University |
| SP-P1.5: A CRITICAL EVALUATION OF STOCHASTIC ALGORITHMS FOR CONVEX OPTIMIZATION |
| Simon Wiesler; RWTH Aachen University |
| Alexander Richard; RWTH Aachen University |
| Ralf Schlüter; RWTH Aachen University |
| Hermann Ney; RWTH Aachen University |
| SP-P1.6: ADAPTIVE BOOSTED NON-UNIFORM MCE FOR KEYWORD SPOTTING ON SPONTANEOUS SPEECH |
| Chao Weng; Georgia Institute of Technology |
| Biing-Hwang (Fred) Juang; Georgia Institute of Technology |
| SP-P1.7: MULTI-TASK LEARNING IN DEEP NEURAL NETWORKS FOR IMPROVED PHONEME RECOGNITION |
| Michael Seltzer; Microsoft Corporation |
| Jasha Droppo; Microsoft Corporation |
| SP-P1.8: DEEP HIERARCHICAL BOTTLENECK MRASTA FEATURES FOR LVCSR |
| Zoltán Tüske; RWTH Aachen University |
| Ralf Schlüter; RWTH Aachen University |
| Hermann Ney; RWTH Aachen University |
| SP-P1.9: MULTI-LEVEL ADAPTIVE NETWORKS IN TANDEM AND HYBRID ASR SYSTEMS |
| Peter Bell; University of Edinburgh |
| Pawel Swietojanski; University of Edinburgh |
| Steve Renals; University of Edinburgh |
| SP-P1.10: INCOHERENT TRAINING OF DEEP NEURAL NETWORKS TO DE-CORRELATE BOTTLENECK FEATURES FOR SPEECH RECOGNITION |
| Yebo Bao; University of Science and Technology of China |
| Hui Jiang; York University |
| Li-Rong Dai; University of Science and Technology of China |
| Cong Liu; Anhui USTC iFLYTEK Corporation Limited |
| SP-P1.11: PHONE RECOGNITION WITH DEEP SPARSE RECTIFIER NEURAL NETWORKS |
| Laszlo Toth; Research Group on Artificial Intelligence |
| SP-P1.12: WARPED MINIMUM VARIANCE DISTORTIONLESS RESPONSE BASED BOTTLE NECK FEATURES FOR LVCSR |
| Kevin Kilgour; Karlsruhe Institute of Technology (KIT) |
| Igor Tseyzer; Karlsruhe Institute of Technology (KIT) |
| Quoc Bao Nguyen; Karlsruhe Institute of Technology (KIT) |
| Alex Waibel; Karlsruhe Institute of Technology (KIT) |
| SP-P1.13: EFFICIENT MANIFOLD LEARNING FOR SPEECH RECOGNITION USING LOCALITY SENSITIVE HASHING |
| Vikrant Tomar; McGill University |
| Richard Rose; McGill University |
| SP-P1.14: TYING ROTATIONS OF COVARIANCE MATRICES VIA RIEMANNIAN SUBSPACE CLUSTERING |
| Yusuke Shinohara; Toshiba Corporation |