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-L5: New Methods for Speech Recognition

Session Type: Lecture
Time: Wednesday, April 22, 09:30 - 11:30
Location: Plenary Hall, TICC
Session Chair: Steve Young, Cambridge University
 
  SPE-L5.1: SINGLE-CHANNEL SPEECH SEPARATION AND RECOGNITION USING LOOPY BELIEF PROPAGATION
         Steven J. Rennie; IBM
         John R. Hershey; IBM
         Peder A. Olsen; IBM
 
  SPE-L5.2: MAXIMIZING THE CONTINUITY IN SEGMENTATION – A NEW APPROACH TO MODEL, SEGMENT AND RECOGNIZE SPEECH
         Ming Ji; Queen's University Belfast
 
  SPE-L5.3: LANGUAGE MODEL TRANSFORMATION APPLIED TO LIGHTLY SUPERVISED TRAINING OF ACOUSTIC MODEL FOR CONGRESS MEETINGS
         Tatsuya Kawahara; Kyoto University
         Masato Mimura; Kyoto University
         Yuya Akita; Kyoto University
 
  SPE-L5.4: AN EVIDENCE FRAMEWORK FOR BAYESIAN LEARNING OF CONTINUOUS-DENSITY HIDDEN MARKOV MODELS
         Yu Zhang; Shanghai Jiao Tong University
         Peng Liu; Microsoft Research Asia
         Jen-Tzung Chien; National Cheng Kung University
         Frank K. Soong; Microsoft Research Asia
 
  SPE-L5.5: A FLAT DIRECT MODEL FOR SPEECH RECOGNITION
         Georg Heigold; RWTH Aachen University
         Geoffrey Zweig; Microsoft Research
         Xiao Li; Microsoft Research
         Patrick Nguyen; Microsoft Research
 
  SPE-L5.6: A PHONETIC FEATURE BASED LATTICE RESCORING APPROACH TO LVCSR
         Sabato Marco Siniscalchi; Norwegian University of Science and Technology (NTNU)
         Torbjørn Svendsen; Norwegian University of Science and Technology (NTNU)
         Chin-Hui Lee; Georgia Institute of Technology
 

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