Login Paper Search My Schedule Paper Index Help

My ICASSP 2009 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.

SPE-P10: Acoustic Modeling II

Session Type: Poster
Time: Thursday, April 23, 10:00 - 12:00
Location: Poster Area D, TICC
Session Chair: Richard Rose, McGill University
 
  SPE-P10.1: EXPERIMENTING WITH A GLOBAL DECISION TREE FOR STATE CLUSTERING IN AUTOMATIC SPEECH RECOGNITION SYSTEMS
         Jasha Droppo; Microsoft Research
         Alex Acero; Microsoft Research
 
  SPE-P10.2: IMPROVED CLUSTERED HIERARCHICAL TANDEM SYSTEM WITH BOTTOM-UP PROCESSING
         Shuo-Yiin Chang; Graduate Institute of Communication Engineering, National Taiwan University
         Lin-shan Lee; Graduate Institute of Communication Engineering, National Taiwan University
 
  SPE-P10.3: DISCRIMINATIVE PRONUNCIATION LEARNING USING PHONETIC DECODER AND MINIMUM-CLASSIFICATION-ERROR CRITERION
         Oriol Vinyals; University of California, Berkeley
         Li Deng; Microsoft Corporation
         Dong Yu; Microsoft Corporation
         Alex Acero; Microsoft Corporation
 
  SPE-P10.4: REVISITING GRAPHEMES WITH INCREASING AMOUNTS OF DATA
         Yun-Hsuan Sung; Stanford University
         Thad Hughes; Google
         Francoise Beaufays; Google
         Brian Strope; Google
 
  SPE-P10.5: PHONEME RECOGNITION USING SPECTRAL ENVELOPE AND MODULATION FREQUENCY FEATURES
         Samuel Thomas; Idiap Research Institute
         Sriram Ganapathy; Idiap Research Institute
         Hynek Hermansky; Idiap Research Institute
 
  SPE-P10.6: CONTEXT-DEPENDENT PRONUNCIATION MODELING FOR IRAQI ASR
         Stavros Tsakalidis; BBN Technologies
         Rohit Prasad; BBN Technologies
         Prem Natarajan; BBN Technologies
 
  SPE-P10.7: TRAINING AND ADAPTING MLP FEATURES FOR ARABIC SPEECH RECOGNITION
         Junho Park; Cambridge University
         Frank Diehl; Cambridge University
         Mark J. F. Gales; Cambridge University
         Marcus Tomalin; Cambridge University
         Philip Woodland; Cambridge University
 
  SPE-P10.8: MULTI-LAYER RATIO SEMI-DEFINITE CLASSIFIERS
         Jon Malkin; Universiity of Washington, Seattle
         Jeff Bilmes; Universiity of Washington, Seattle
 
  SPE-P10.9: SEMI-TIED COVARIANCE MATRICES FOR ACOUSTIC MODELS BASED ON RANDOM FORESTS OF PHONETIC DECISION TREES
         Jian Xue; IBM
         Lili Che; IBM
         Yunxin Zhao; University of Missouri - Columbia
 
  SPE-P10.10: REFACTORING ACOUSTIC MODELS USING VARIATIONAL DENSITY APPROXIMATION
         Pierre Dognin; IBM
         John R. Hershey; IBM
         Vaibhava Goel; IBM
         Peder A. Olsen; IBM
 
  SPE-P10.11: PHMM BASED ASYNCHRONOUS ACOUSTIC MODEL FOR CHINESE LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
         Hao Wu; Peking University
         Xihong Wu; Peking University
         Huisheng Chi; Peking University
 
  SPE-P10.12: DISCRIMINATIVE TRAINING OF HIERARCHICAL ACOUSTIC MODELS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
         Hung-An Chang; MIT Computer Science and Artificial Intelligence Laboratory
         James R. Glass; MIT Computer Science and Artificial Intelligence Laboratory
 

©2016 Conference Management Services, Inc. -||- email: webmaster@icassp09.com -||- Last updated Thursday, January 22, 2009