In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...
In this paper, we analyze the performance of name finding in the context of a variety of automatic speech recognition (ASR) systems and in the context of one optical character rec...
David R. H. Miller, Sean Boisen, Richard M. Schwar...
Collecting supervised training data for automatic speech recognition (ASR) systems is both time consuming and expensive. In this paper we use the notion of virtual evidence in a g...
The Multi-Stream automatic speech recognition approach was investigated in this work as a framework for Audio-Visual data fusion and speech recognition. This method presents many ...
We present a data-mining experiment on feature selection for automatic emotion recognition. Starting from more than 1000 features derived from pitch, energy and MFCC time series, ...