Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
This paper examines tagging models for spontaneous English speech transcripts. We analyze the performance of state-of-the-art tagging models, either generative or discriminative, ...
Vladimir Eidelman, Zhongqiang Huang, Mary P. Harpe...
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
A major shortcoming of discriminative recognition and detection methods is their noise sensitivity, both during training and recognition. This may lead to very sensitive and britt...
The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a non-linear generative model of handwritten images of digits. The q...