Publications

In this work, we develop a statistical model of pitch that allows unbiased estimation of pitch statistics from pitch tracks which are subject to doubling and/or halving.

We present an N-best rescoring algorithm that removes the effect of segmentation mismatch. Furthermore, we show that explicit language modeling of hidden linguistic segment boundaries is improved by including turn-boundary…

We show that the standard hypothesis scoring paradigm used in maximum-likelihood-based speech recognition systems is not optimal with regard to minimizing the word error rate, the commonly used performance metric…

In this paper, we propose a new algorithm to train mixtures of transformation networks (MTNs) in the hybrid connectionist recognition framework. We apply the new algorithm to nonnative speaker adaptation,…

We describe an algorithm based on acoustic clustering and acoustic adaptation to significantly improve speech recognition performance. The method is particularly useful when speech from multiple speakers is to be…

We present a maximum entropy language model that incorporates both syntax and semantics via a dependency grammar.

In this article, we use our interaction model to demonstrate that during multimodal fusion, speech should be a privileged modality, driving the interpretation of a query, and that in certain…

We present a novel approach to hidden Markov model (HMM) state clustering based on the use of broad phone classes and an allophone class entropy measure. Our algorithm allows clustering…

This paper describes our work in developing multilingual (Swedish and English) speech recognition systems in the ATIS domain. The acoustic component of the multilingual systems is realized through sharing Gaussian…

In the context of automatic speaker recognition, we propose a model transformation technique that renders speaker models more robust to acoustic mismatches and to data scarcity by appropriately increasing their…