Articles

This paper presents Trace & Unification Gram- mar (TUG), a declarative and reversible grammar formalism that brings together Unification Gram- mar (uG) and ideas of Government & Binding Theory (GB) in an undogmatic way. A grammar compiler is presented that transforms a grammar written in the TUG formalism into two …...

The GE NLTooLSET is a set of text interpretation tools designed to be easily adapted to new domains. This report summarizes the system and its performance on the MUG-3 task....

This paper reports on the GE NLTooLsET customization effort for MUC-3, and analyzes th e results of the TST2 run . Although our own tests had shown steady improvement between TST1 and TST2, our official scores on TST2 were lower than on TST1 . The analysis of this unexpected result …...

This paper presents a study of military applications of advanced speech processing technology which includes three major elements: (1) review and assessment of cur- rent efforts in military applications of speech technol- ogy; (2) identification of opportunities for future mili- tary applications of advanced speech technology; and (3) identification of …...

We have developed an algorithm for the automatic conversion of dictated English sentences to written text, with essentially no restriction on the nature of the mate- rial dictated. We require that speakers undergo a short training session so that the system can adapt to their individual speaking characteristics and that …...

This paper describes the tree-structured maximum mutual information (MMI) encoders used in SSrs Phonetic Engine ® to perform large-vocabulary, continuous speech recognition. The MMI encoders are arranged into a two-stage cascade. At each stage, the encoder is trained to maximize the mutual information between a set of phonetic targets and …...

A model-based spectral estimation algorithm is derived that improves the robustness of speech recognition systems to additive noise. The algorithm is tailored for filter-bank-based systems, where the estimation should seek to minimize the distortion as measured by the recognizer's distance metric. This estimation criterion is approximated by minimizing the Euclidean …...

This paper reports recent efforts to further improve the perfor- mance of the Sphinx system for speaker-independent contin- uous speech recognition. The recognition error rate is signifi- cantly reduced with incorporation of additional dynamic fea- tures, semi-continuous hidden Markov models, and speaker clustering. For the June 1990 (RM2) evaluation test …...

We report on some recent improvements to an HMM- based, continuous speech recognition system which is being developed at AT&T Bell Laboratories. These advances, which include the incorporation of inter-word, context-dependent units and an improved feature analysis, lead to a recognition system which achieves better than 95% word accuracy for …...

Most large vocabulary speech recognition systems essentially consist of a training algorithm and a recognition structure which is essentially a search for the best path through a rather large decoding network. Although the performance of the recognizer is crucially tied to the details of the training procedure, it is absolutely …...

This paper reports on two contributions to large vocabu- lary continuous speech recognition. First, we present a new paradigm for speaker-independent (SI) training of hid- den Markov models (HMM), which uses a large amount of speech from a few speakers instead of the traditional prac- tice of using a little …...

The Lincoln robust HMM recognizer has been con- verted from a single Ganssian or Gaussian mixture pdf per state to tied mixtures in which a single set of Gaus- sians is shared between all states. There were some initial difficulties caused by the use of mixture pruning [12] but these …...

This paper presents recent natural language work on HARC, the BBN Spoken Language System. The HARC system in- corporates the Byblos system [6] as its speech recognition component and the natural language system Delphi, which consists of a bottom-up parser paired with an integrated syn- tax/semantics unification grammar, a discourse …...

The stack decoder is an attractive algorithm for con- trolling the acoustic and language model matching in a continuous speech recognizer. It implements a best-first tree search of the language to find the best match to both the language model and the observed speech. This paper describes a method for …...

Phonetic baseforms are the basic recognition units in most large vocabulary speech recognition systems. These base- forms are usually determined by hand once a vocabulary is chosen and not modified thereafter. However, many applica- tions of speech recognition, such as dictation transcription, are hampered by a fixed vocabulary and require …...

In this paper we present methods for reducing the compu- tation time of joint segmentation and recognition of phones using the Stochastic Segment Model (SSM). Our approach to the problem is twofold: first, we present a fast segment classification method that reduces computation by a factor of 2 to 4, …...

This paper describes an algorithm for performing rapid match on continuous speech that makes it possible to rec- ognize sentences from an 842 word vocabulary on a desk- top 33 megahertz 80486 computer in near real time. This algorithm relies on a combination of smoothing and linear segmentation together with …...

For large-vocabulary continuous speech recognition, the goal of training is to model phonemes with enough precision so that from the models one could reconstruct a sequence of acoustic parameters that accurately represents the spectral characteristics of any naturally-occurring sentence, including all coarticuladon effects that arise either between phonemes in a …...

One of the problems for all speech input is the necessity for the talker to be encumbered by a head. mounted, hand-held, or fixed position microphone. An intelfigent, electronically-aimed unidirectional micro- phone would overcome this problem. Array tech- niques hold the best promise to bring such a system to practicality. …...

Spoken language systems for the near future will not handle all of English, but, rather, will be limited to a domain-specific sub-language. Accurate modeling of the sub-language will depend on analysis of domain-specific data. Since no spoken language systems currently have a wide range of users, and since variability across …...