Technical Program
SP-P1: Acoustic Model Adaptation for Speech Recognition I |
| Session Type: Poster |
| Time: Tuesday, March 22, 13:30 - 15:30 |
| Location: Poster Area H |
| Session Chair: Malcolm Slaney, Google Machine Hearing Research |
| SP-P1.1: CONTEXT ADAPTIVE DEEP NEURAL NETWORKS FOR FAST ACOUSTIC MODEL ADAPTATION IN NOISY CONDITIONS |
| Marc Delcroix; NTT Corporation |
| Keisuke Kinoshita; NTT Corporation |
| Chengzhu Yu; University of Texas at Dallas |
| Atsunori Ogawa; NTT Corporation |
| Takuya Yoshioka; NTT Corporation |
| Tomohiro Nakatani; NTT Corporation |
| SP-P1.2: ON COMBINING I-VECTORS AND DISCRIMINATIVE ADAPTATION METHODS FOR UNSUPERVISED SPEAKER NORMALIZATION IN DNN ACOUSTIC MODELS |
| Lahiru Samarakoon; National University of Singapore |
| Khe Chai Sim; National University of Singapore |
| SP-P1.3: SPEAKER-AWARE TRAINING OF LSTM-RNNS FOR ACOUSTIC MODELLING |
| Tian Tan; Shanghai Jiao Tong University |
| Yanmin Qian; Shanghai Jiao Tong University |
| Dong Yu; Microsoft Research |
| Souvik Kundu; National University of Singapore |
| Liang Lu; University of Edinburgh |
| Khe Chai Sim; National University of Singapore |
| Xiong Xiao; Nanyang Technological University |
| Yu Zhang; Massachusetts Institute of Technology |
| SP-P1.4: NON-NEGATIVE INTERMEDIATE-LAYER DNN ADAPTATION FOR A 10-KB SPEAKER ADAPTATION PROFILE |
| Kshitiz Kumar; Microsoft Corporation |
| Chaojun Liu; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SP-P1.5: SPEAKER ADAPTIVE TRAINING IN DEEP NEURAL NETWORKS USING SPEAKER DEPENDENT BOTTLENECK FEATURES |
| Rama Doddipatla; Toshiba Research Europe Limited |
| SP-P1.6: SPEAKER CLUSTER-BASED SPEAKER ADAPTIVE TRAINING FOR DEEP NEURAL NETWORK ACOUSTIC MODELING |
| Wei Chu; Sony Computer Entertainment America |
| Ruxin Chen; Sony Computer Entertainment America |
| SP-P1.7: DNN SPEAKER ADAPTATION USING PARAMETERISED SIGMOID AND RELU HIDDEN ACTIVATION FUNCTIONS |
| Chao Zhang; University of Cambridge |
| Philip Woodland; University of Cambridge |
| SP-P1.8: SPEAKER ADAPTATION OF RNN-BLSTM FOR SPEECH RECOGNITION BASED ON SPEAKER CODE |
| Zhiying Huang; University of Science and Technology of China |
| Jian Tang; University of Science and Technology of China |
| Shaofei Xue; University of Science and Technology of China |
| Li-Rong Dai; University of Science and Technology of China |
| SP-P1.9: EFFICIENT NON-LINEAR FEATURE ADAPTATION USING MAXOUT NETWORKS |
| Steven Rennie; IBM Research |
| Xiaodong Cui; IBM Research |
| Vaibhava Goel; IBM Research |
| SP-P1.10: SEQUENCE SUMMARIZING NEURAL NETWORK FOR SPEAKER ADAPTATION |
| Karel Vesely; BUT |
| Shinji Watanabe; Mitsubishi Electric Research Laboratories |
| Katerina Zmolikova; BUT |
| Martin Karafiat; BUT |
| Lukas Burget; BUT |
| Jan Cernocky; BUT |
ICASSP 2016 Patrons
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |