Login Paper Search My Schedule Paper Index Help

My ICASSP 2019 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.

HLT-P1: Language modeling, ASR and Punctuation Prediction

Session Type: Poster
Time: Tuesday, May 14, 17:30 - 19:30
Location: Poster Area C, Ground Floor
Session Chair: Dilek Hakkani-Tür, Amazon Alexa AI
 
  HLT-P1.1: KNOWLEDGE DISTILLATION FOR RECURRENT NEURAL NETWORK LANGUAGE MODELING WITH TRUST REGULARIZATION
         Yangyang Shi; Mobvoi AI Lab
         Mei-Yuh Hwang; Mobvoi AI Lab
         Xin Lei; Mobvoi AI Lab
         Haoyu Sheng; Williams College
 
  HLT-P1.2: GAUSSIAN PROCESS LSTM RECURRENT NEURAL NETWORK LANGUAGE MODELS FOR SPEECH RECOGNITION
         Max W. Y. Lam; Chinese University of Hong Kong
         Xie Chen; Microsoft
         Shoukang Hu; Chinese University of Hong Kong
         Jianwei Yu; Chinese University of Hong Kong
         Xunying Liu; Chinese University of Hong Kong
         Helen Meng; Chinese University of Hong Kong
 
  HLT-P1.3: INVESTIGATION OF SAMPLING TECHNIQUES FOR MAXIMUM ENTROPY LANGUAGE MODELING TRAINING
         Xie Chen; Microsoft
         Jun Zhang; Microsoft
         Tasos Anastasakos; Microsoft
         Fil Alleva; Microsoft
 
  HLT-P1.4: IMPROVEMENTS TO N-GRAM LANGUAGE MODEL USING TEXT GENERATED FROM NEURAL LANGUAGE MODEL
         Masayuki Suzuki; IBM
         Nobuyasu Itoh; IBM
         Tohru Nagano; IBM
         Gakuto Kurata; IBM
         Samuel Thomas; IBM
 
  HLT-P1.5: A UNIFIED FRAMEWORK FOR FEATURE-BASED DOMAIN ADAPTATION OF NEURAL NETWORK LANGUAGE MODELS
         Michael Hentschel; Nara Institute of Science and Technology
         Marc Delcroix; NTT Communication Science Laboratories
         Atsunori Ogawa; NTT Communication Science Laboratories
         Tomoharu Iwata; NTT Communication Science Laboratories
         Tomohiro Nakatani; NTT Communication Science Laboratories
 
  HLT-P1.6: IMPROVING SPEECH RECOGNITION ERROR PREDICTION FOR MODERN AND OFF-THE-SHELF SPEECH RECOGNIZERS
         Prashant Serai; The Ohio State University
         Peidong Wang; The Ohio State University
         Eric Fosler-Lussier; The Ohio State University
 
  HLT-P1.7: RECURRENT NEURAL NETWORK LANGUAGE MODEL TRAINING USING NATURAL GRADIENT
         Jianwei Yu; the Chinese University of Hong Kong
         Max W. Y. Lam; the Chinese University of Hong Kong
         Xie Chen; Microsoft AI and Research
         Shoukang Hu; the Chinese University of Hong Kong
         Songxiang Liu; the Chinese University of Hong Kong
         Xixin Wu; the Chinese University of Hong Kong
         Xunying Liu; the Chinese University of Hong Kong
         Helen Meng; the Chinese University of Hong Kong
 
  HLT-P1.8: CONTEXT-AWARE NEURAL-BASED DIALOG ACT CLASSIFICATION ON AUTOMATICALLY GENERATED TRANSCRIPTIONS
         Daniel Ortega; University of Stuttgart
         Chia-Yu Li; University of Stuttgart
         Gisela Vallejo; University of Stuttgart
         Pavel Denisov; University of Stuttgart
         Ngoc Thang Vu; University of Stuttgart
 
  HLT-P1.9: SELF-ATTENTION BASED MODEL FOR PUNCTUATION PREDICTION USING WORD AND SPEECH EMBEDDINGS
         Jiangyan Yi; Institute of Automation, Chinese Academy of Sciences
         Jianhua Tao; Institute of Automation, Chinese Academy of Sciences
 
  HLT-P1.10: EMPIRICAL EVALUATION AND COMBINATION OF PUNCTUATION PREDICTION MODELS APPLIED TO BROADCAST NEWS
         Alexandre Nanchen; Idiap Research Institute
         Philip N. Garner; Idiap Research Institute
 
  HLT-P1.11: DEEP RECURRENT NEURAL NETWORKS WITH LAYER-WISE MULTI-HEAD ATTENTIONS FOR PUNCTUATION RESTORATION
         Seokhwan Kim; Adobe Research