Search Results - "Rohlicek, J.R."

Parameter estimation of dependence tree models using the EM algorithm by Ronen, O., Rohlicek, J.R., Ostendorf, M.

“…A dependence tree is a model for the joint probability distribution of an n-dimensional random vector, which requires a relatively small number of free…”
Get full text

Fast algorithms for phone classification and recognition using segment-based models by Digalakis, V.V., Ostendorf, M., Rohlicek, J.R.

“…Methods for reducing the computation requirements of joint segmentation and recognition of phones using the stochastic segment model are presented. The…”
Get full text

Approaches to topic identification on the switchboard corpus by McDonough, J., Ng, K., Jeanrenaud, P., Gish, H., Rohlicek, J.R.

“…Topic identification (TID) is the automatic classification of speech messages into one of a known set of possible topics. The TID task can be view as having…”
Get full text

Lattice-based search strategies for large vocabulary speech recognition by Richardson, F., Ostendorf, M., Rohlicek, J.R.

“…The design of search algorithms is an important issue in large vocabulary speech recognition, especially as more complex models are developed for improving…”
Get full text

A dynamical system approach to continuous speech recognition by Digalakis, V., Rohlicek, J.R., Ostendorf, M.

“…An dynamical system model is proposed for better representing the spectral dynamics of speech for recognition. It is assumed that the observed feature vectors…”
Get full text

ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition by Digalakis, V., Rohlicek, J.R., Ostendorf, M.

“…A nontraditional approach to the problem of estimating the parameters of a stochastic linear system is presented. The method is based on the…”
Get full text

Joint quantizer design and parameter estimation for discrete hidden Markov models by Ostendorf, M., Rohlicek, J.R.

“…An approach that involves designing a vector quantizer to maximize the mutual information between the hidden Markov model (HMM) states and the quantized…”
Get full text

Spotting events in continuous speech by Jeanrenaud, P., Siu, M., Rohlicek, J.R., Meteer, M., Gish, H.

“…Jeanrenaud et al. (1993) introduced the notion of event spotting and showed that the detection of events could be approached as a word spotting problem. The…”
Get full text

Statistical language modeling combining N-gram and context-free grammars by Meteer, M., Rohlicek, J.R.

“…Linguistic structure in the form of a partial-coverage phrase structure grammar is combined with statistical N-gram techniques. The result is a robust…”
Get full text

Statistical language modeling using a small corpus from an application domain by Rohlicek, J.R., Yen-Lu Chow, Roucos, S.

“…Statistical language models have been successfully used to improve the performance of continuous speech recognition algorithms. Application of such techniques…”
Get full text

A linguistic feature representation of the speech waveform by Eide, E., Rohlicek, J.R., Gish, H., Mitter, S.

“…Linguistic theory views a phoneme as a shorthand notation for a bundle of binary features related to the operation of the speaker's articulators. A…”
Get full text

Phonetic training and language modeling for word spotting by Rohlicek, J.R., Jeanrenaud, P., Ng, K., Gish, H., Musicus, B., Siu, M.

“…The authors present a view of HMM (hidden Markov model)-based word spotting systems as described by three main components: the HMM acoustic model; the overall…”
Get full text

Continuous hidden Markov modeling for speaker-independent word spotting by Rohlicek, J.R., Russell, W., Roukos, S., Gish, H.

“…A word-spotting system using Gaussian hidden Markov models is presented. Several aspects of this problem are investigated. Specifically, results are reported…”
Get full text

Robust mapping of noisy speech parameters for HMM word spotting by Ng, K., Gish, H., Rohlicek, J.R.

“…It is demonstrated that using the proposed probabilistic vector mapping algorithm as a feature preprocessor results in robust performance levels across a wide…”
Get full text

A Bayesian approach to speaker adaptation for the stochastic segment model by Necioglu, B.F., Ostendorf, M., Rohlicek, J.R.

“…Speaker adaptation is frequently used to achieve good speech recognition performance without the high costs associated with training a speaker-dependent model…”
Get full text

Probabilistic vector mapping of noisy speech parameters for HMM word spotting by Gish, H., Chow, Y.L., Rohlicek, J.R.

“…A conditional probability model is developed for relating a noisy, observation feature vector to the noise-free vector that generated it. The model is a…”
Get full text

Maximum likelihood clustering of Gaussians for speech recognition by Kannan, A., Ostendorf, M., Rohlicek, J.R.

“…Describes a method for clustering multivariate Gaussian distributions using a maximum likelihood criterion. The authors point out possible applications of…”
Get full text

Gisting conversational speech in real time by Denenberg, L., Gish, H., Meteer, M., Miller, T., Rohlicek, J.R., Sadkin, W., Siu, M.

“…The authors describe additions and modifications to a prototype system for analyzing air traffic contol (ATC) communication. The primary goal of the effort was…”
Get full text

Gisting conversational speech by Rohlicek, J.R., Ayuso, D., Bates, M., Bobrow, R., Boulanger, A., Gish, H., Jeanrenaud, P., Meteer, M., Siu, M.

“…A novel system for extracting information from stereotyped voice traffic is described. Off-the-air recordings of commercial air traffic control communications…”
Get full text

Time Scale Decomposition: The Role of Scaling in Linear Systems and Transient States in Finite-State Markov Processes by Lou, X.-C., Rohlicek, J.R., Coxson, P.G., Verghese, G.C., Willsky, A.S.

Get full text