Speech & natural language publications

We present a novel noise-robust feature extraction algorithm that is a combination of our previously developed minimum mean square error (MMSE) log-energy estimation algorithm and the probabilistic optimum filtering (POF)…

We present an approach to cluster the training data for automatic speech recognition (ASR). A relative entropy based distance metric between training data clusters is defined.

We explore supervised speaker adaptation and normalization in the MLP component of a hybrid hidden Markov model/multilayer perceptron version of SRI's DECIPHER™ speech recognition system. Our approach combines both adaptation…

Acoustic properties of disfluent repetitions are examined to investigate two proposed functions of repeating. Repeating may serve as a filler while hesitating; alternatively, repeating may function to bridge a gap…

I propose a fine structure of the preferential interpretation in pragmatics in terms of defeasible rule interactions. A logical implementation of the preferential rule interactions is proposed using prioritized circumscription,…

Irrespective of whether our goal is the eventual automation of interpreted, telephone calls, or simply the support of human interpreters during such calls, our ultimate success would be enhanced by…

We propose two schemes for incorporating distinctive speech features (sonorant, fricative, nasal, vocalic, and voiced) into the MLP component of our system. We show a small improvement in recognition performance…

In this paper we present a training method and a network architecture for estimating context-dependent observation probabilities in the framework of a hybrid hidden Markov model (HMM) / multi layer…

This chapter reviews application areas in which spoken interaction may play a significant role, assesses potential benefits of spoken interaction with machines, and attempts to compare voice with alternative and…

The paper describes the architecture of Gemini, paying particular attention to resolving the tension between robustness and overgeneration. Gemini features a broad-coverage unification-based grammar of English, fully interleaved syntactic and…

In this paper we discuss a Gender Dependent Neural Network (GDNN) which can be tuned for each gender, while sharing most of the speaker independent parameters. We use a classification…

The system marks the location and extent of a repair, as well as relevant words in the region of the repair. Together these labels determine the relationship between the "error"…