Ensemble de recherches dont l'objectif est de mettre en œuvre des systemes de dialogue homme-machine possedant un comportement aussi naturel que possible. L'etude des informations temporelles, qui touchent tous les niveaux de traitement d'un systeme de dialogue, est privilegiee. Un modele cognitif de representation du temps est propose. Il permet de considerer sous un meme angle des phenomenes lies au langage, a la representation des connaissances et au raisonnement.

Vers la définition d'un modèle cognitif autour de la représentation du temps dans un système de dialogue Homme-Machine

The use of the Dempster-Shafer rule in the lexical component of a man-machine oral dialogue system

MYRTILLE II is a system which is now being implemented at CRIN in order to understand a wide subset of natural spoken French. In this paper we will concentrate on the syntactic-semantic component of the system. The general principle and overall architecture of MYRTILLE II are first briefly described. The way in which syntax and semantics are integrated in a unified representation is then presented. This representation is equivalent to a network with procedural nodes. Several examples of processed sentences are finally discussed. The system yields a tree structure of an input sentence. The examples presented show how syntax and semantics are used for solving typical problems which occur in speech understanding.

Syntactic--Semantic interpretation of sentences in the MYRTILLE II speech understanding system

In the framework of MYRTILLE II Speech Understanding System under development in our Laboratory we have realized a prototype for the acoustic-phonetic processing level. This prototype makes it possible to test various parameters and strategies for phonemic transcription of continuous speech. It can be considered as a metasystem in the sense that, given a hierarchy of recognition algorithms and a strategy, it can generate the optimal system for phoneme recognition. The system directly works on the digitized speech wave, which makes it possible to get the best accuracy on the parameters. The speech signal is segmented into phoneme-like units by a decision function which incorporates voicing, energy, zero-crossing rate and curve length. The segments thus obtained are then processed by the recognition system which can be viewed as a tree structure the nodes of which are algorithms. These algorithms take into account one or several features and their answers can be phoneme classes and/or other algorithms. Problems involved in the design of such a system are also presented in this paper together with a particular implementation.

An experimental system for acoustic-phonetic decoding of continuous speech

The use of speech in man-machine communication is becoming increasingly important and research in this area is now a part of computer science activity, related both to signal processing, pattern recognition and artificial intelligence. The actual applications of speech recognition presently use isolated word recognition systems but the most interesting and promising domains of man-machine dialog will require connected speech recognition and understanding. Although significant results have already been obtained (see for instance (1)) the presently available systems obviously have still to be improved.

Semantic and Pragmatic Processing in Continuous Speech Understanding

The Signal Processing and Pattern Recognition Group in Nancy is developing the MYRTILLE System for recognizing and understanding sentences in artificial and natural languages. A model for the oral control of a telephone exchange with an artificial language was proposed and described at ICASSP 76. In this paper, we first present a comparative study of two syntactic models that we have used concurrently in this experiment : a classical top-down model and a generalized bottom-up, island-driven model. Then, we discuss the generalization of this model to natural language understanding system (e.g. for the oral consultation of a data base). Such a generalization involves a very different structure, which is described in details.

http://ieeexplore.ieee.org/iel6/8365/26347/01170303.pdf

J.-F. Mari

Papers

Research towards speech understanding models for artificial and natural languages