Judith Hochberg

Automatic script identification from document images using cluster-based templates

We describe an automated script identification system for typeset document images. Templates for each script are created by clustering textual symbols from a training set. Symbols from new images are compared to the templates to find the best script. Our current system processes thirteen scripts with minimal preprocessing and high accuracy.

NADIR: An automated system for detecting network intrusion and misuse

This paper describes a misuse detection system for Los Alamos National Laboratorys Integrated Computing Network (ICN). This automated expert system, the Network Anomaly Detection and Intrusion Reporter (NADIR), streamlines and supplements the manual audit record review traditionally performed by security auditors. NADIR compares network activity, as summarized in weekly profiles of individual users and the ICN as a whole, against expert rules that define security policy and improper or suspicious behaviour. NADIR reports suspicious behaviour to security auditors and provides tools to aid in follow-up investigations. This paper describes analysis by NADIR of two types of ICN activity: user authentication and access control, and mass file storage. It highlights system design issues of data handling, exploiting existing auditing systems, and performing audit analysis at the network level.

Inferring articulation and recognizing gestures from acoustics with a neural network trained on x‐ray microbeam data

This paper describes a method for inferring articulatory parameters from acoustics with a neural network trained on paired acoustic and articulatory data. An x-ray microbeam recorded the vertical movements of the lower lip, tongue tip, and tongue dorsum of three speakers saying the English stop consonants in repeated Ce syllables. A neural network was then trained to map from simultaneously recorded acoustic data to the articulatory data. To evaluate learning, acoustics from the training set were passed through the neural network. To evaluate generalization, acoustics from speakers or consonants excluded from the training set were passed through the network. The articulatory trajectories thus inferred were a good fit to the actual movements in both the learning and generalization conditions, as judged by root-mean-square error and correlation. Inferred trajectories were also matched to templates of lower lip, tongue tip, and tongue dorsum release gestures extracted from the original data. This technique correctly recognized from 94.4% to 98.9% of all gestures in the learning and cross-speaker generalization conditions, and 75% of gestures underlying consonants excluded from the training set. In addition, greater regularity was observed for movements of articulators that were critical in the formation of each consonant.

Script and language identification for handwritten document images

Abstract. A system for automatically identifying the script used in a handwritten document image is described. The system was developed using a 496-document dataset representing six scripts, eight languages, and 279 writers. Documents were characterized by the mean, standard deviation, and skew of five connected component features. A linear discriminant analysis was used to classify new documents, and tested using writer-sensitive cross-validation. Classification accuracy averaged 88% across the six scripts. The same method, applied within the Roman subcorpus, discriminated English and German documents with 85% accuracy.

Quality assessment and restoration of typewritten document images

Abstract. We present a useful method for assessing the quality of a typewritten document image and automatically selecting an optimal restoration method based on that assessment. We use five quality measures that assess the severity of background speckle, touching characters, and broken characters. A linear classifier uses these measures to select a restoration method. On a 139-document corpus, our methodology reduced the corpus OCR character error rate from 20.27% to 12.60%.

A default hierarchy for pronouncing English

The authors study the principles governing the power and efficiency of the default hierarchy, a system of knowledge acquisition and representation. The default hierarchy trains automatically, yet yields a set of rules which can be easily assessed and analyzed. Rules are organized in a hierarchical structure containing general (default) and specific rules. In training the hierarchy, general rules are learned before specific rules. In using the hierarchy, specific rules are accessed first, with default rules used when no specific rules apply. The main results concern the properties of the default hierarchy architecture, as revealed by its application to English pronunciation. Evaluating the hierarchy as a pronouncer of English, the authors find that its rules capture several key features of English spelling. The default hierarchy pronounces English better than the neural network NETtalk, and almost as well as expert-devised systems. >

An animated display of tongue, lip and jaw movements during speech: A proper basis for speech aids to the handicapped and other speech technologies

The authors have developed a method for inferring articulatory parameters from acoustics. For this method, an X-ray microbeam records the movements of the lower lip, tongue tip and tongue dorsum during normal speech. A neural network is then trained to map from concurrently recorded acoustic data to the articulatory data. The device has applications in speech therapy as a lip-reading aid, and as a basis for other speech technologies including speech and speaker recognition and low data-rate speech transmission.<<ETX>>

An efficient default hierarchy for pronouncing English

A default hierarchy induction paradigm was trained to translate English words from standard orthography into their phonetic transcriptions. Associations between letters and phonemes were established by building a hierarchy of rules. The most common rules, at the lowest level of the hierarchy, are based on single letter‐to‐phoneme correspondences. Higher level rules, taking into account contexts of increasing numbers of surrounding letters, capture exceptions with respect to lower levels. The hierarchy of rules is then used to pronounce words in a test set by searching the rule structure from the highest to the lowest level. A previous version of this paradigm, called “HIERtalker” [An et al., Proceedings of the IEEE Int. Conf. on Neural Networks, Vol. II, 221–228 (1988)], used only rules in which the letter being pronounced was centered in its context of surrounding letters. Further work has shown that efficiency (in the sense of requiring fewer rules) is improved by the use of left‐ and right‐oriented rul...