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...
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...
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 ...
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...
The acceleration of acoustic likelihood calculation has been an important research issue for developing practical speech recognition systems. And there are various specification ...