Technical Program

SP-P9: Acoustic Modeling II

Session Type: Poster

Time: Thursday, March 18, 10:00 - 12:00

Location: Poster Area D

Session Chair: Enrico Bocchieri, AT&T Research, USA

SP-P9.1: USING DURATION AND PITCH FOR MANDARIN DIGIT STRING RECOGNITION

Rui Zhao; Toshiba

Yusuke Kida; Toshiba

Xiang Yan; Toshiba

Pei Ding; Toshiba

Lei He; Toshiba

SP-P9.2: MAXIMUM ENTROPY BASED TONE MODELING FOR MANDARIN SPEECH RECOGNITION

Xinhao Wang; Peking University

Yansuo Yu; Peking University

Xihong Wu; Peking University

Huisheng Chi; Peking University

SP-P9.3: DIMENSIONALITY REDUCTION METHODS FOR HMM PHONETIC RECOGNITION

Hongbing Hu; Binghamton University

Stephen Zahorian; Binghamton University

SP-P9.4: IMPROVING SPEECH RECOGNITION BY EXPLICIT MODELING OF PHONE DELETIONS

Tom Ko; The Hong Kong University of Science and Technology

Brian Mak; The Hong Kong University of Science and Technology

SP-P9.5: USING BURST ONSET INFORMATION TO IMPROVE STOP/AFFRICATE PHONE RECOGNITION

Chi-Yueh Lin; National Tsing Hua University

Hsiao-Chuan Wang; National Tsing Hua University

SP-P9.6: MULTI-STYLE MLP FEATURES FOR BN TRANSCRIPTION

Viet Bac Le; LIMSI-CNRS

Lori Lamel; LIMSI-CNRS

Jean-Luc Gauvain; LIMSI-CNRS

SP-P9.7: SPEAKER ADAPTATION BASED ON THE MULTILINEAR DECOMPOSITION OF TRAINING SPEAKER MODELS

Yongwon Jeong; Pusan National University

SP-P9.8: INVESTIGATIONS ON ENSEMBLE BASED UNSUPERVISED ADAPTATION METHODS

Yu Kubota; Tokyo Institute of Technology

Takahiro Shinozaki; Tokyo Institute of Technology

Sadaoki Furui; Tokyo Institute of Technology

SP-P9.9: EFFICIENT ONLINE LEARNING WITH INDIVIDUAL LEARNING-RATES FOR PHONEME SEQUENCE RECOGNITION

Koby Crammer; Technion - Israel Institute of Technology

SP-P9.10: EXPERIMENTAL STUDIES ON CONTINUOUS SPEECH RECOGNITION USING NEURAL ARCHITECTURES WITH “ADAPTIVE” HIDDEN ACTIVATION FUNCTIONS

Sabato Marco Siniscalchi; Norwegian University of Science and Technology

Torbjørn Svendsen; Norwegian University of Science and Technology

Filippo Sorbello; Unipa

Chin-Hui Lee; Georgia Institute of Technology

SP-P9.11: ANALYSIS OF PHONE POSTERIOR FEATURE SPACE EXPLOITING CLASS-SPECIFIC SPARSITY AND MLP-BASED SIMILARITY MEASURE

Afsaneh Asaei; Idiap Research Institute and Ecole Polytechnique Fédérale de Lausanne (EPFL)

Benjamin Picart; TCTS Lab, Faculté Polytechnique, Université de Mons

Herve Bourlard; Idiap Research Institute and Ecole Polytechnique Fédérale de Lausanne (EPFL)

SP-P9.12: GMM-HMM ACOUSTIC MODEL TRAINING BY A TWO LEVEL PROCEDURE WITH GAUSSIAN COMPONENTS DETERMINED BY AUTOMATIC MODEL SELECTION

Dan Su; Peking University

Xihong Wu; Peking University

Lei Xu; Chinese University of Hong Kong