Showing papers on "Perplexity published in 1991"

A dynamic language model for speech recognition

Abstract: In the case of a trigram language model, the probability of the next word conditioned on the previous two words is estimated from a large corpus of text. The resulting static trigram language model (STLM) has fixed probabilities that are independent of the document being dictated. To improve the language model (LM), one can adapt the probabilities of the trigram language model to match the current document more closely. The partially dictated document provides significant clues about what words are more likely to be used next. Of many methods that can be used to adapt the LM, we describe in this paper a simple model based on the trigram frequencies estimated from the partially dictated document. We call this model a cache trigram language model (CTLM) since we are caching the recent history of words. We have found that the CTLM reduces the perplexity of a dictated document by 23%. The error rate of a 20,000-word isolated word recognizer decreases by about 5% at the beginning of a document and by about 24% after a few hundred words.

Development and preliminary evaluation of the MIT ATIS system

Abstract: This paper represents a status report on the MIT ATIS system. The most significant new achievement is that we now have a speech-input mode. It is based on the MIT SUMMIT system using context independent phone models, and includes a word-pair grammar with perplexity 92 (on the June-90 test set). In addition, we have completely redesigned the back-end component, in order to emphasize portability and extensibility. The parser now produces an intermediate semantic frame representation, which serves as the focal point for all back-end operations, such as history management, text generation, and SQL query generation. Most of those aspects of the system that are tied to a particular domain are now entered through a set of tables associated with a small artificial language for decoding them. We have also improved the display of the database table, making it considerably easier for a subject to comprehend the information given. We report here on the results of the official DARPA February-91 evaluation, as well as on results of an evaluation on data collected at MIT, for both speech input and text input.

Alguns pontos sobre a história da crítica genética

Abstract: What is the "genetic criticism", that was called by the critic Louis Hay in 1979?What do we do when we deal with the genetic criticism? This article defines a new interdisciplinary field, which has caused perplexity amongst the literary theorists and critics. The most importam moments (positive and negative) of the reception of the genetic criticism are stressed.

Phonetic typewriter based on phoneme source modeling

Abstract: A phonetic typewriter that utilizes the underlying statistical structure of phoneme/character sequences is described. The syllable/character trigram approach to language modeling is adopted to make language source models. These are obtained by calculating trigram probabilities, using a large text database. The phonetic typewriter is tested using 279 phrases uttered by one male speaker, and the syllable source model achieves a 94.9% phoneme recognition rate with the test-set phoneme perplexity of 3.9. Without the syllable trigram, the phoneme recognition rate is only 73.2%. A trigram model based on characters is also evaluated. This model can reduce the phoneme perplexity significantly compared with that of the syllable trigram. >

Aspectos psicossociais da Síndrome da Imunodeficiência Adquirida

Abstract: Psychosocial aspects which arise with regard to people directly or indirectly involved with AIDS: patients, relatives and professional staff, are studied. The results show that the population assisted in the Ribeirao Preto region is predominantly young, male and drug-addicted. The patients with "positive" results show reactions similar to those described by Kluber-Ross (1977) for terminal patients. The behavior observed in relatives forms a continuum which varies from the negation of the illness to the overprotection of the patient. For the professionals, perplexity is the most common reaction when they face a population which is different from that with which they are used to dealing. Finally, the data acquired indicate that the psychologist can help the professionals to deal with the reactions of the patients by integrating them into their organic and emotional aspects.

The SSI large-vocabulary speaker-independent continuous speech recognition system

Abstract: The Speech Systems Incorporated (SSI) commercial, large-vocabulary, speaker-independent, continuous speech recognition system is described. The system utilizes a novel approach to speech representation: a two-stage encoding of speech, with an intervening compression of acoustic frames (segmentation) between the encoding stages, and a linguistic decoding process suitable for large, variable-duration segments. Binary decision trees trained using the maximum mutual information (MMI) criterion serve as encoders. The features used in encoding are listed, and their ability to discriminate the phonetic content of the speech is analyzed. Recognition results are given for a speaker-independent continuous speech, grammar-constrained radiology reporting product, and for an isolated-word grammar of high perplexity. >

El aprovechamiento de la perplejidad en la filosofía doctrinal en Kant

Abstract: The aim of this paper is to show how Kant, in constructing his systematic philosophy, makes both implicit and explicit use of his critical solution to the problem of perplexity, which derives from the mismatch between the demand for cognitive com-pleteness and the limitation of objective knowledge.