In this paper we present an approach to recognition confidence scoring and a set of techniques for integrating confidence scores into the understanding and dialogue components of ...
Timothy J. Hazen, Stephanie Seneff, Joseph Polifro...
We explore morphology-based and sub-word language modeling approaches proposed for morphologically rich languages, and evaluate and contrast them for Turkish broadcast news transc...
Long-span features, such as syntax, can improve language models for tasks such as speech recognition and machine translation. However, these language models can be difficult to u...
The first stage in many pattern recognition tasks is to generate a good set of features from the observed data. Usually, only a single feature space is used. However, in some compl...
The Gaussian mixture model (GMM) can approximate arbitrary probability distributions, which makes it a powerful tool for feature representation and classification. However, it su...