Although initially introduced and studied in the late 1960s and early 1970s, statistical methods of Markov source or hidden Markov modeling have become increasingly popular in the last several years. There are two strong reasons why this has occurred. First the models are very rich in mathematical structure and hence can form the theoretical basis for use in a wide range of applications. Sec-ond the models, when applied properly, work very well in practice for several important applications. In this paper we attempt to care-fully and methodically review the theoretical aspects of this type of statistical modeling and show how they have been applied to selected problems in machine recognition of speech. I.

In this paper an original method for integrating Artificial Neural Networks (ANN) with Hidden Markov Models (HMM) is proposed. ANNs are suitable to perform phonetic classification, whereas HMMs have been proven successful at modeling the temporal structure of the speech signal. In the approach described here, the ANN outputs constitute the sequence of observation vectors for the HMM. An algorithm is proposed for global optimization of all the parameters. Results on speaker-independent recognition experiments using this integrated ANN-HMM system on the TIMIT continuous speech database are reported. 1 Introduction In spite of the fact that speech exhibits features that cannot be represented by a first-order Markov model, Hidden Markov Models (HMMs) of speech units (e.g., phonemes) have been used with a good degree of success in Automatic Speech Recognition (ASR) (Rabiner & Levinson 85; Lee & Hon 89). Artificial Neural Networks (ANNs) have proven to be useful for classifying speech prop...

This paper describes a large vocabulary handwritten word recognition system based on a syntax#directed level building algorithm #SDLBA# that incorporates contextual information. The sequences of observations extracted from the input images are matched against the entries of a tree#structure lexicon where each node is represented bya 10#state character HMM. The search proceeds breadth---#rst and each node is decoded by the SDLBA. Contextual information about writing styles and case transitions is injected between the levels of the SDLBA.

We apply an HMM-based text recognition system to the recognition of handwritten digit strings of unknown length. The algorithm is tailored to the input data by controlling the maximum number of levels searched by the Level Building (LB) search algorithm. We demonstrate that setting this parameter according to the pixel length of the observation sequence, rather than using a fixed value for all input data, results in a faster and more accurate system. Best results were achieved by setting the maximum number of levels to twice the estimated number of characters in the input string. We also describe experiments which show the potential for further improvement by using an adaptive termination criterion in the LB search. 1. Introduction Hidden Markov models (HMMs) [5] have been widely used in the field of speech recognition for many years [4], but have only recently begun to receive a similar degree of attention in the context of text recognition [1, 3]. The HMM approach is particularly su...

This report is concerned with the development of tools needed to provide a system such as an expert system with the ability to automatically build and update its knowledge base through the analysis of technical material that is in natural language (and machine-readable) form. These tools include both those that are needed to perform the natural language processing tasks that are required (the natural language component) and those that are needed to extract the relevant information from the text and appropriately store it in the knowledge base (the knowledge representation and acquisition component). The text that is being used as a testbed for this project is the Merck Veterinary Manual

This report highlights our current work and accomplishments on the project to exploit angular diversity for improved target detection in multi-aperture SAR images. This report also contains a brief introduction to hidden Markov models, and identifies issues which we will resolve as work continues. We have analyzed multi-aperture SAR images and demonstrated that anisotropic behavior is present in our multi-aperture SAR image set. We performed baselining studies using the common method of CFAR LTT detection and formulated an HMM detection method using Baum-Welch reestimation to train HMMs to represent target, tree clutter, and ground clutter pixels. Our results show that HMM detection produced significantly better results than CFAR LTT detection (with a 29-by-29 reference window) for the y This research was supported by Wright Laboratory. z The SPANN Lab's WWW URL is http://eewww.eng.ohio-state.edu/research/spann/. same multi-aperture SAR image and requires less computation. Speci...

We have developed a set of interactive tools for collecting, annotating, and analyzing group communication sessions. These tools have been used to model group meetings which we have enacted on our computer-based video conferencing system as well as single location meetings. The purpose of this work is to support the analysis of group meetings over computer-based video conferencing systems. The resulting analysis can be used for various purposes including creating meeting summaries, identifying communication patterns, facilitating group communication, and suggesting agendas for follow-on meetings. The current system is used for off-line annotation and analysis of communication sessions which involve various parallel media tracks including the video and audio component for each participant, the text transcription of the meeting, and various documents and media forms referenced during the session. In this paper we review these tools and describe an architecture for employing these techniq...

this paper, semi-continuous HMMs (SCHMMs) (Bellagarda & Nahamoo 89; Huang & Jack 89) and continuous densities HMMs (CDHMMs) will be considered in conjunction with networks trained with the generalized delta rule (Rumelhart et al 86). It will be shown how to perform a joint global optimi ation of both the ANN and the HMM parameter estimation. In the proposed algorithm, the gradient of the optimization criterion with respect to the transformed observations is computed for the HMM system. The HMM can be trained with traditional methods (Rabiner 89) with which the gradient of an optimization criterion is computed. This gradient is sent to the ANN for the estimation of the weight associated to each connection of the network. No assumption need to be made or constraints imposed on the network outputs, except that the network output distribution should be modeled by a mixture of multivariate gaussians. Since training of HMMs is usually much faster than ANN training, we consider how to initialize the ANN in order to start from parameter values that are not too far from those obtained after training. Multiple ANNs are combined and an incremental design method is described in which specialized networks are integrated to the recognition system in order to improve its performance. Relate or Interesting papers have been published recently, describing attempts at com-

A study of several methods for combining information from two classifiers in a system for the recognition of handwritten text is presented. The system uses two hidden Markov models (HMMs) per character to model columns and rows of pixels in the character image. We show that the best method of combining the results from the vertical and horizontal classifiers is simply to multiply the probabilities produced by the two methods. This approach outperforms more complicated classifier combination strategies such as the behavior-knowledge space (BKS) method. 1. Introduction The combination of multiple classifiers has proved to be a powerful technique in many areas of pattern recognition research. Usually, for a specific recognition problem, there are a number of possible classification algorithms available, often based on different theories or methodologies, and perhaps using different feature sets. The performance of a method is likely to depend on a number of known or unknown factors, mak...

Contents 1 Introduction 1 2 The Human Speech 3 2.1 Phonemes : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 3 2.1.1 Other Speech Units : : : : : : : : : : : : : : : : : : : : : 4 2.2 Kinds of Phonemes : : : : : : : : : : : : : : : : : : : : : : : : : : 5 2.2.1 Consonants : : : : : : : : : : : : : : : : : : : : : : : : : : 5 2.2.1.1 Voicing : : : : : : : : : : : : : : : : : : : : : : : 6 2.2.1.2 Place of Articulation : : : : : : : : : : : : : : : 6 2.2.1.3 Manner of Articulation : : : : : : : : : : : : : : 7 2.2.2 Vowels : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 8 2.2.3 Diphthongs : : : : : : : : : : : : : : : : : : : : : : : : : : 8 2.3 Formants : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 9 3 A Signal Processing View of the Human Speech 10 3.1 Def