Technical Program

SP-P10: Discriminative Training/Search

Session Type: Poster

Time: Thursday, March 18, 13:30 - 15:30

Location: Poster Area A

Session Chair: Hong-Kwang Jeff Kuo, IBM T. J. Watson Research Center, USA

SP-P10.1: DISCRIMINATIVE TRAINING BASED ON AN INTEGRATED VIEW OF MPE AND MMI IN MARGIN AND ERROR SPACE

Erik McDermott; NTT Corporation

Shinji Watanabe; NTT Corporation

Atsushi Nakamura; NTT Corporation

SP-P10.2: THE EFFECT OF LATTICE PRUNING ON MMIE TRAINING

Long Qin; Carnegie Mellon University

Alexander Rudnicky; Carnegie Mellon University

SP-P10.3: PARALLEL IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK TRAINING

Stefano Scanzio; Politecnico di Torino

Sandro Cumani; Politecnico di Torino

Roberto Gemello; Politecnico di Torino

Franco Mana; Politecnico di Torino

Pietro Laface; Politecnico di Torino

SP-P10.4: I-SMOOTH FOR IMPROVED MINIMUM CLASSIFICATION ERROR TRAINING

Haozheng Li; National Research Council of Canada

Cosmin Munteanu; National Research Council of Canada

SP-P10.5: LEARNING TASK-DEPENDENT SPEECH VARIABILITY IN DISCRIMINATIVE ACOUSTIC MODEL ADAPTATION

Shoei Sato; NHK (Japan Broadcasting Corporation)

Takahiro Oku; NHK (Japan Broadcasting Corporation)

Shinichi Homma; NHK (Japan Broadcasting Corporation)

Akio Kobayashi; NHK (Japan Broadcasting Corporation)

Toru Imai; NHK (Japan Broadcasting Corporation)

SP-P10.6: A BOUNDED TRUST REGION OPTIMIZATION FOR DISCRIMINATIVE TRAINING OF HMMS IN SPEECH RECOGNITION

Cong Liu; University of Science and Technology of China

Yu Hu; University of Science and Technology of China

Hui Jiang; York University

Li-Rong Dai; University of Science and Technology of China

SP-P10.7: PHONE MODELING AND COMBINING DISCRIMINATIVE TRAINING FOR MANDARIN-ENGLISH BILINGUAL SPEECH RECOGNITION

Yanmin Qian; Tsinghua University

Jia Liu; Tsinghua University

SP-P10.8: A DISCRIMINATIVE MODEL FOR CONTINUOUS SPEECH RECOGNITION BASED ON WEIGHTED FINITE STATE TRANSDUCERS

Shinji Watanabe; NTT Communication Science Laboratories, NTT Corporation

Takaaki Hori; NTT Communication Science Laboratories, NTT Corporation

Erik McDermott; NTT Communication Science Laboratories, NTT Corporation

Atsushi Nakamura; NTT Communication Science Laboratories, NTT Corporation

SP-P10.9: AN INITIAL ATTEMPT FOR PHONEME RECOGNITION USING STRUCTURED SUPPORT VECTOR MACHINE (SVM)

Hao Tang; National Taiwan University

Chao-Hong Meng; National Taiwan University

Lin-Shan Lee; National Taiwan University

SP-P10.10: AN EFFICIENT BEAM PRUNING WITH A REWARD CONSIDERING THE POTENTIAL TO REACH VARIOUS WORDS ON A LEXICAL TREE

Tsuneo Kato; KDDI R&D Laboratories Inc.

Kengo Fujita; KDDI R&D Laboratories Inc.

Nobuyuki Nishizawa; KDDI R&D Laboratories Inc.

SP-P10.11: SEARCH ERROR RISK MINIMIZATION IN VITERBI BEAM SEARCH FOR SPEECH RECOGNITION

Takaaki Hori; NTT Corporation

Shinji Watanabe; NTT Corporation

Atsushi Nakamura; NTT Corporation

SP-P10.12: AN IMPROVED CONSENSUS-LIKE METHOD FOR MINIMUM BAYES RISK DECODING AND LATTICE COMBINATION

Haihua Xu; Shanghai Jiao Tong University

Daniel Povey; Microsoft

Lidia Mangu; IBM

Jie Zhu; Shanghai Jiao Tong University