Login Paper Search My Schedule Paper Index Help

My ICASSP 2016 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Clicking on the Add button next to a paper title will add that paper to your custom schedule.
Clicking on the Remove button next to a paper will remove that paper from your custom schedule.

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