Login Paper Search My Schedule Paper Index Help

My ICASSP 2017 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-P3: Acoustic Modeling II

Session Type: Poster
Time: Monday, March 6, 16:00 - 18:00
Location: Churchill: Poster Area A
Session Chair: Liang Lu, Toyota Technological Institute at Chicago
 
  SP-P3.1: PERSONALIZED ACOUSTIC MODELING BY WEAKLY SUPERVISED MULTI-TASK DEEP LEARNING USING ACOUSTIC TOKENS DISCOVERED FROM UNLABELED DATA
         Cheng-Kuan Wei; National Taiwan University
         Cheng-Tao Chung; National Taiwan University
         Hung-Yi Lee; National Taiwan University
         Lin-Shan Lee; National Taiwan University
 
  SP-P3.2: UNSUPERVISED UTTERANCE-WISE BEAMFORMER ESTIMATION WITH SPEECH RECOGNITION-LEVEL CRITERION
         Takuya Higuchi; NTT Corporation
         Takuya Yoshioka; NTT Corporation
         Keisuke Kinoshita; NTT Corporation
         Tomohiro Nakatani; NTT Corporation
 
  SP-P3.3: CUMULATIVE MOVING AVERAGED BOTTLENECK SPEAKER VECTORS FOR ONLINE SPEAKER ADAPTATION OF CNN-BASED ACOUSTIC MODELS
         Tsubasa Ochiai; NTT Corporation / Doshisha University
         Marc Delcroix; NTT Corporation
         Keisuke Kinoshita; NTT Corporation
         Atsunori Ogawa; NTT Corporation
         Taichi Asami; NTT Corporation
         Shigeru Katagiri; Doshisha University
         Tomohiro Nakatani; NTT Corporation
 
  SP-P3.4: UNSUPERVISED ADAPTATION FOR DEEP NEURAL NETWORKS USING ALTERNATING DIRECTION METHOD OF MULTIPLIERS
         Roger Hsiao; Raytheon BBN Technologies
         Tim Ng; Raytheon BBN Technologies
         Man-Hung Siu; Raytheon BBN Technologies
 
  SP-P3.5: DOMAIN ADAPTATION OF DNN ACOUSTIC MODELS USING KNOWLEDGE DISTILLATION
         Taichi Asami; NTT Corporation
         Ryo Masumura; NTT Corporation
         Yoshikazu Yamaguchi; NTT Corporation
         Hirokazu Masataki; NTT Corporation
         Yushi Aono; NTT Corporation
 
  SP-P3.6: EFFECTIVE JOINT TRAINING OF DENOISING FEATURE SPACE TRANSFORMS AND NEURAL NETWORK BASED ACOUSTIC MODELS
         Takashi Fukuda; IBM Research - Tokyo
         Osamu Ichikawa; IBM Research - Tokyo
         Gakuto Kurata; IBM Research - Tokyo
         Ryuki Tachibana; IBM Research - Tokyo
         Samuel Thomas; IBM T.J. Watson Research Center
         Bhuvana Ramabhadran; IBM T.J. Watson Research Center
 
  SP-P3.7: HARMONIC FEATURE FUSION FOR ROBUST NEURAL NETWORK-BASED ACOUSTIC MODELING
         Osamu Ichikawa; IBM Research - Tokyo
         Takashi Fukuda; IBM Research - Tokyo
         Masayuki Suzuki; IBM Research - Tokyo
         Gakuto Kurata; IBM Research - Tokyo
         Bhuvana Ramabhadran; IBM T.J. Watson Research Center
 
  SP-P3.8: TOWARDS PHONEME INVENTORY DISCOVERY FOR DOCUMENTATION OF UNWRITTEN LANGUAGES
         Markus Müller; Karlsruhe Institute of Technology
         Jörg Franke; Karlsruhe Institute of Technology
         Alex Waibel; Karlsruhe Institute of Technology
         Sebastian Stüker; Karlsruhe Institute of Technology
 
  SP-P3.9: JOINT MODELING OF ARTICULATORY AND ACOUSTIC SPACES FOR CONTINUOUS SPEECH RECOGNITION TASKS
         Vikramjit Mitra; SRI International
         Ganesh Sivaraman; University of Maryland
         Chris Bartels; SRI International
         Hosung Nam; Korea University
         Wen Wang; SRI International
         Carol Espy-Wilson; University of Maryland
         Dimitra Vergyri; SRI International
         Horacio Franco; SRI International