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...
Large vocabulary continuous speech recognition (LVCSR) systems traditionally represent words in terms of smaller subword units. Both during training and during recognition, they re...
In this paper, we extend our previous study on discriminative training using non-uniform criteria for speech recognition. The work will put emphasis on how the acoustic modeling i...
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...
In this paper we show how common speech recognition training criteria such as the Minimum Phone Error criterion or the Maximum Mutual Information criterion can be extended to inco...