2005 IEEE International Conference on Acoustics, Speech, and Signal Processing
March 18-23, 2005 • Pennsylvania Convention Center/Marriott Hotel • Philadelphia, PA, USA
ICASSP
30th Anniversary
SP-P9: Acoustic Modeling and Clustering Algorithms |
| Session Type: Poster |
| Time: Tuesday, March 22, 09:30 - 11:30 |
| Location: CC: Poster 2 |
| Chair: Chris Wellekens, Institut Eurecom |
| SP-P9.1: INITIALIZING SUBSPACE CONSTRAINED GAUSSIAN MIXTURE MODELS |
| Peder Olsen; IBM |
| Karthik Visweswariah; IBM |
| Ramesh Gopinath; IBM |
| SP-P9.2: MULTI-RATE AND VARIABLE-RATE MODELING OF SPEECH AT PHONE AND SYLLABLE TIME SCALES |
| Özgür Cetin; University of Washington |
| Mari Ostendorf; University of Washington |
| SP-P9.3: OPTIMAL CLUSTERING AND NON-UNIFORM ALLOCATION OF GAUSSIAN KERNELS IN SCALAR DIMENSION FOR HMM COMPRESSION |
| Xiao-Bing Li; ATR Spoken Language Translation Research Labs |
| Frank K. Soong; ATR Spoken Language Translation Research Labs |
| Tor André Myrvoll; Norwegian University of Science and Technology |
| Ren-Hua Wang; University of Science and Technology of China |
| SP-P9.4: HIERARCHICAL CORRELATION COMPENSATION FOR HIDDEN MARKOV MODELS |
| Hui Lin; Tsinghua University |
| Ye Tian; Microsoft Research Asia |
| JianLai Zhou; Microsoft Research Asia |
| Hui Jiang; York University |
| SP-P9.5: CLUSTER-DEPENDENT ACOUSTIC MODELING |
| Bing Xiang; BBN Technologies |
| Long Nguyen; BBN Technologies |
| Spyros Matsoukas; BBN Technologies |
| Richard Schwartz; BBN Technologies |
| SP-P9.6: FUZZY PARAMETER CLUSTERING METHOD IN SPEECH RECOGNITION |
| Xianghua Xu; Shanghai Jiaotong University |
| Jie Zhu; Shanghai Jiaotong University |
| SP-P9.7: AUTOMATIC TRAINING SET SEGMENTATION FOR MULTI-PASS SPEECH RECOGNITION |
| Mark Mao; Stanford University |
| Vincent Vanhoucke; Nuance Communications |
| Brian Strope; Nuance Communications |
| SP-P9.8: GENERALIZED STATISTICAL MODELING OF PRONUNCIATION VARIATIONS USING VARIABLE-LENGTH PHONE CONTEXT |
| Yuya Akita; Kyoto University |
| Tatsuya Kawahara; Kyoto University |
| SP-P9.9: ON INITIALIZATION OF GAUSSIAN MIXTURES: A HYBRID GENETIC EM ALGORITHM |
| Franz Pernkopf; Graz University of Technology |
| SP-P9.10: ACOUSTIC MODEL TRAINING USING GREEDY EM |
| Rusheng Hu; University of Missouri-Columbia |
| Xiaolong Li; University of Missouri-Columbia |
| Yunxin Zhao; University of Missouri-Columbia |
| SP-P9.11: MODELING SUCCESSIVE FRAME DEPENDENCIES WITH HYBRID HMM/BN ACOUSTIC MODEL |
| Konstantin Markov; ATR Spoken Language Translation Research Labs |
| Satoshi Nakamura; ATR Spoken Language Translation Research Labs |
| SP-P9.12: IMPROVED COVARIANCE MODELING FOR MAXIMUM LIKELIHOOD MULTIPLE SUBSPACE TRANSFORMATIONS |
| Xi Zhou; University of Science and Technology of China |
| Ye Tian; Microsoft Research Asia |
| JianLai Zhou; Microsoft Research Asia |
| Bei-qian Dai; University of Science and Technology of China |