Articles

In this paper we discuss recent results from our efforts to make SPHINX, the CMU continuous-speech speaker- independent recognition system, robust to changes in the environment. To deal with differences in noise level and spectral tilt between close-talking and desk-top microphones, we describe two novel methods based on ad- ditive …...

Speech research has made tremendous progress in the past using the following paradigm: • define the research problem, • collect a corpus to objectively measure progress, and • solve the research problem. Natural language research, on the other hand, has typ- ically progressed without the benefit of any corpus of …...

Progress can be measured and encouraged via standards for comparison and evaluation. Though qualitative as- sessments can be useful in initial stages, quantifiable measures of systems under the same conditions are es- sential for comparing results and assessing claims. This paper will address the emerging standards for evaluation of spoken …...

SRI and U.C. Berkeley have begun a cooper- ative effort to develop a new architecture for real-time implementation of spoken language systems (SLS). Our goal is to develop fast speech recognition algorithms, and support- ing hardware capable of recognizing continu- ous speech from a bigram- or trigram-based 20,000-word vocabulary or …...

We present a 1000-word continuous speech recognition (CSR) system that operates in real time on a personal computer (PC). The system, designed for large vocabulary natural language tasks, makes use of phonetic Hidden Markov models (HMM) and incorporates acoustic, phonetic, and linguistic sources of knowledge to achieve high recognition performance. …...

We describe the methods and hardware that we are using to produce a real-time demonstration of an integrated Spo- ken Language System. We describe algorithms that greatly reduce the computation needed to compute the N-Best sen- tence hypotheses. To avoid grammar coverage problems we use a fully-connected first-order statistical class …...

With the onslaught of various natural language pro- cessing (NLP) systems and their respective applica- tions comes the inevitable task of determining a way in which to compare and thus evaluate the output of these systems. This paper focuses on one such evalua- tion technique that originated from the text …...

. Despite numerous investigations into English tense-aspect semantics, the problem of formally inter- preting tense and aspect remains in large part unsolved. A formal solution requires (a) a well-defined mapping from a subset of English covering the most common tense-aspect constructions (including embedded tensed clauses) to a formal meaning representation, …...

We describe the modification of a grammar to take ad- vantage of prosodic information automatically extracted from speech. The work includes (1) the development of an integer "break index" representation of prosodic phrase boundary information, (2) the automatic detec- tion of prosodic phrase breaks using a hidden Markov model on …...

In this paper a new, tree-trellis based fast search for finding the N best sentence hypotheses in continuous speech recognition is proposed. The search consists of two parts: a forward, time-synchronous, trellis search and a backward, time asynchronous, tree search. In the first module the well known Viterbi algorithm is …...

We present two efficient search algorithms for real-time spo- ken language systems. The first called the Word-Dependent N-Best algorithm is an improved algorithm for finding the top N sentence hypotheses. The new algorithm is shown to perform as well as the Exact Sentence-Dependent al- gorithm presented previously but with an …...

ion and Anaphora Mark Johnson Brown University Martin Kay Xerox Pale Alto Research Center and Stanford University Abstract This paper describes a way of expressing syn- tactic rules that ~kssociate semantic formulae with strings, but in a manner thai is inde- pendent of the syntactic details of these for- mulac. …...

: The paper presents an integrated environment for morphological analysis of word-forms of the Slovene language. The system consists of a lexicon input and maintenance module, a lexicon output module for accessing lexical word forms, a two-level rule compiler and a two-level morphological analysis/synthesis unit. The basic paradigms and lexical …...

We present here the current prototype of the text understanding system HELENE. The ob- jective of this system is to achieve a deep un- derstanding of small reports dealing with a re- stricted domain. Sentence understanding builds a model of the state of the world described, through the application of …...

A style checker is a tool which supports authors during the process of writing: Certain style markers are analyzed, their values are compared with a given norm, deviations are detected, and recommendations are given to the author. The power of a style checker depends on available tools such as lexica, …...

STS is a small experimental sentence translation system developed to demonstrate the efficiency of our lexicalist model of translation. Based on a GB-inspired parser, lexical transfer and lexi- cal projection, STS provides real-time accurate English translations for a small but non-trivial subset of French sentences. 1...

This article introduces a bidirectional grammar generation system called feature structure-directed generation, developed for a dialogue translation system. The system utilizes typed feature structures to control the top-down derivation in a declarative way. This generation system also uses disjunctive feature structures to reduce the number of copies of the derivation …...

: Description of a connectionist implementation of an Earley parser. 1....

THALES is a software package for plane geometry constructions, supplied with a natural language interlace. Using THALES requires no knowledge of a programming language. The interface is capable of processing practically all kinds of instructions within the subset of plane geometry English. The "static semantic" module has been generated on …...

Recent work in text analysis has suggested that data on words that frequently occur to- gether reveal important information about text content. Co-occurrence relations can serve two main purposes in language pro- cessing. First, the statistics of co-occurrence have been shown to produce accurate results in syntactic analysis. Second, the …...