Technical Program
SP-P16: Speech Adaptation |
Session Type: Poster |
Time: Friday, May 31, 08:00 - 10:00 |
Location: Poster Area D |
Session Chair: DeLiang Wang, The Ohio State University |
SP-P16.1: UNSUPERVISED DISCRIMINATIVE ADAPTATION USING DIFFERENCED MAXIMUM MUTUAL INFORMATION BASED LINEAR REGRESSION |
Marc Delcroix; Nippon Telegraph and Telephone Corporation |
Atsunori Ogawa; Nippon Telegraph and Telephone Corporation |
Seong-Jun Hahm; Nippon Telegraph and Telephone Corporation |
Tomohiro Nakatani; Nippon Telegraph and Telephone Corporation |
Atsushi Nakamura; Nippon Telegraph and Telephone Corporation |
SP-P16.2: KL-DIVERGENCE REGULARIZED DEEP NEURAL NETWORK ADAPTATION FOR IMPROVED LARGE VOCABULARY SPEECH RECOGNITION |
Dong Yu; Microsoft Research |
Kaisheng Yao; Microsoft Corporation |
Hang Su; Microsoft Research Asia |
Gang Li; Microsoft Research Asia |
Frank Seide; Microsoft Research Asia |
SP-P16.3: FEATURE SPACE VARIATIONAL BAYESIAN LINEAR REGRESSION AND ITS COMBINATION WITH MODEL SPACE VBLR |
Seong-Jun Hahm; Nippon Telegraph and Telephone Corporation |
Atsunori Ogawa; Nippon Telegraph and Telephone Corporation |
Marc Delcroix; Nippon Telegraph and Telephone Corporation |
Masakiyo Fujimoto; Nippon Telegraph and Telephone Corporation |
Takaaki Hori; Nippon Telegraph and Telephone Corporation |
Atsushi Nakamura; Nippon Telegraph and Telephone Corporation |
SP-P16.4: RAPID ADAPTATION FOR MOBILE SPEECH APPLICATIONS |
Michiel Bacchiani; Google Inc. |
SP-P16.5: TEMPORAL FILTER DESIGN BY MINIMUM KL DIVERGENCE CRITERION FOR ROBUST SPEECH RECOGNITION |
Xiong Xiao; Nanyang Technological University |
Eng-Siong Chng; Nanyang Technological University |
Haizhou Li; Institute for Infocomm Research |
SP-P16.6: SPEAKER ADAPTIVE KULLBACK-LEIBLER DIVERGENCE BASED HIDDEN MARKOV MODELS |
David Imseng; Idiap Research Institute |
Hervé Bourlard; Idiap Research Institute |
SP-P16.7: UNSUPERVISED ADAPTATION WITHOUT ESTIMATED TRANSRIPTIONS |
Hyeopwoo Lee; Speech Information Processing Laboratory, Korea University |
Dongsuk Yook; Speech Information Processing Laboratory, Korea University |
SP-P16.8: NON-LINEAR FREQUENCY WARPING FOR VTLN USING SUBGLOTTAL RESONANCES AND THE THIRD FORMANT FREQUENCY |
Harish Arsikere; University of California, Los Angeles |
Steven M. Lulich; Indiana University, Bloomington |
Abeer Alwan; University of California, Los Angeles |
SP-P16.9: LEARNING DISCRIMINATIVE BASIS COEFFICIENTS FOR EIGENSPACE MLLR UNSUPERVISED ADAPTATION |
Yajie Miao; Carnegie Mellon University |
Florian Metze; Carnegie Mellon University |
Alex Waibel; Carnegie Mellon University |
SP-P16.10: TANDEM SYSTEM ADAPTATION USING MULTIPLE LINEAR FEATURE TRANSFORMS |
Yongqiang Wang; Cambridge University |
Mark J.F. Gales; Cambridge University |
SP-P16.11: PHONETIC SUBSPACE ADAPTATION FOR AUTOMATIC SPEECH RECOGNITION |
Sina Hamidi Ghalehjegh; McGill University |
Richard Rose; McGill University |
SP-P16.12: FAST SPEAKER ADAPTATION OF HYBRID NN/HMM MODEL FOR SPEECH RECOGNITION BASED ON DISCRIMINATIVE LEARNING OF SPEAKER CODE |
Ossama Abdel-Hamid; York University |
Hui Jiang; York University |
SP-P16.13: SPEAKER ADAPTATION OF CONTEXT DEPENDENT DEEP NEURAL NETWORKS |
Liao Hank; Google Inc. |