Sciweavers

127 search results - page 9 / 26
» Advances in Large Vocabulary Continuous Speech Recognition
Sort
View
INTERSPEECH
2010
13 years 2 months ago
A discriminative splitting criterion for phonetic decision trees
Phonetic decision trees are a key concept in acoustic modeling for large vocabulary continuous speech recognition. Although discriminative training has become a major line of rese...
Simon Wiesler, Georg Heigold, Markus Nußbaum...
ACL
2001
13 years 8 months ago
Processing Broadcast Audio for Information Access
This paper addresses recent progress in speaker-independent, large vocabulary, continuous speech recognition, which has opened up a wide range of near and mid-term applications. O...
Jean-Luc Gauvain, Lori Lamel, Gilles Adda, Martine...
ICPR
2008
IEEE
14 years 8 months ago
A phone-viseme dynamic Bayesian network for audio-visual automatic speech recognition
This work extends and improves a recently introduced (Dec. 2007) dynamic Bayesian network (DBN) based audio-visual automatic speech recognition (AVASR) system. That system models ...
Louis H. Terry, Aggelos K. Katsaggelos
ACL
2011
12 years 11 months ago
Learning Sub-Word Units for Open Vocabulary Speech Recognition
Large vocabulary speech recognition systems fail to recognize words beyond their vocabulary, many of which are information rich terms, like named entities or foreign words. Hybrid...
Carolina Parada, Mark Dredze, Abhinav Sethy, Ariya...
CSL
2004
Springer
13 years 7 months ago
Factor analysed hidden Markov models for speech recognition
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covaria...
Antti-Veikko I. Rosti, M. J. F. Gales