Neural Network and Information Theory In Automatic Speech Understanding

Salma Jamoussi (1) , Kamel Smaïli (1) , Jean-Paul Haton (1)

1 PAROLE - Analysis, perception and recognition of speech

In this paper, we present two methods for speech understanding : an artificial neural network and an information theory based method. For both methods we have to index input sentences using semantic classes (or concepts). In the first method, we perform supervised learning and we obtain very good indexing results. In the second one, we propose a new method based on mutual information statistical measure to retrieve concepts, and also to tag each sentence by its concepts. Both methods have been tested on a tourist information corpus. The information theory method yields better recall, whereas the neural network achieves a better precision. Better performance has been obtained by the neural network method (about 4%).

Mots clés: statistical measures; speech understanding; neural networks; information theory; mutual information

Mots clés: compréhension de la parole; réseaux de neurones; théorie de l'information; information mutuelle; mesures statistiques

Domaines: Autre [cs.OH]

Salma Jamoussi, Kamel Smaïli, Jean-Paul Haton. Neural Network and Information Theory In Automatic Speech Understanding. SPECOM 2002 - International Workshop Speech and Computer, 2002, St-Petersburg, Russia. pp.1-4. ⟨inria-00100827⟩