SP-P5: LVCSR |
| Session Type: Poster |
| Time: Wednesday, March 28, 10:30 - 12:30 |
| Location: Poster Area B
|
| Session Chairs: Kate Knill, Toshiba Research Europe and Yasuo Ariki, Kobe University
|
| |
|
SP-P5.1: IMPROVING LANGUAGE MODELS FOR ASR USING TRANSLATED IN-DOMAIN DATA
|
| Stefan Kombrink; Brno University of Technology
|
| Tomas Mikolov; Brno University of Technology
|
| Martin Karafiat; Brno University of Technology
|
| Lukáš Burget; Brno University of Technology
|
| |
|
SP-P5.2: EXPLOITING SPARSENESS IN DEEP NEURAL NETWORKS FOR LARGE VOCABULARY SPEECH RECOGNITION
|
| Dong Yu; Microsoft Research
|
| Frank Seide; Microsoft Research Asia
|
| Gang Li; Microsoft Research Asia
|
| Li Deng; Microsoft Research
|
| |
|
SP-P5.3: IMPROVING ACOUSTIC BASED KEYWORD SPOTTING USING LVCSR LATTICES
|
| Petr Motlicek; IDIAP Research Institute
|
| Fabio Valente; IDIAP Research Institute
|
| Igor Szöke; Brno University of Technology
|
| |
|
SP-P5.4: UNSUPERVISED VOCABULARY SELECTION FOR REAL-TIME SPEECH RECOGNITION OF LECTURES
|
| Paul Maergner; Carnegie Mellon University
|
| Alex Waibel; Karlsruhe Institute of Technology
|
| Ian Lane; Carnegie Mellon University
|
| |
|
SP-P5.5: A LAYERED APPROACH FOR DUTCH LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
|
| Joris Pelemans; Katholieke Universiteit Leuven
|
| Kris Demuynck; Katholieke Universiteit Leuven
|
| Patrick Wambacq; Katholieke Universiteit Leuven
|
| |
|
SP-P5.6: JOINING ADVANTAGES OF WORD-CONDITIONED AND TOKEN-PASSING DECODING
|
| David Nolden; RWTH Aachen University
|
| David Rybach; RWTH Aachen University
|
| Ralf Schlüter; RWTH Aachen University
|
| Hermann Ney; RWTH Aachen University
|
| |
|
SP-P5.7: EXTENDED SEARCH SPACE PRUNING IN LVCSR
|
| David Nolden; RWTH Aachen University
|
| Ralf Schlüter; RWTH Aachen University
|
| Hermann Ney; RWTH Aachen University
|
| |
|
SP-P5.8: USING A* FOR THE PARALLELIZATION OF SPEECH RECOGNITION SYSTEMS
|
| Patrick Cardinal; CRIM
|
| Gilles Boulianne; CRIM
|
| Pierre Dumouchel; ETS
|
| |
|
SP-P5.9: INVESTIGATIONS ON EXEMPLAR-BASED FEATURES FOR SPEECH RECOGNITION TOWARDS THOUSANDS OF HOURS OF UNSUPERVISED, NOISY DATA
|
| Georg Heigold; Google, Inc.
|
| Patrick Nguyen; Google, Inc.
|
| Mitchel Weintraub; Google, Inc.
|
| Vincent Vanhoucke; Google, Inc.
|
| |
|
SP-P5.10: GOOGLE’S CROSS-DIALECT ARABIC VOICE SEARCH
|
| Fadi Biadsy; Google, Inc.
|
| Pedro Moreno; Google, Inc.
|
| Martin Jansche; Google, Inc.
|
| |
|
SP-P5.11: AUTOMATIC ERROR REGION DETECTION AND CHARACTERIZATION IN LVCSR TRANSCRIPTIONS OF TV NEWS SHOWS
|
| Richard Dufour; Orange Labs, France Telecom
|
| Géraldine Damnati; Orange Labs, France Telecom
|
| Delphine Charlet; Orange Labs, France Telecom
|
| |
|
SP-P5.12: IMPROVING ARABIC BROADCAST TRANSCRIPTION USING AUTOMATIC TOPIC CLUSTERING
|
| Stephen Chu; IBM T.J. Watson Research Center
|
| Lidia Mangu; IBM T.J. Watson Research Center
|
| |