Text-Mining Research Group

Sentence Modality Recognition in French based on Prosody

This paper deals with automatic sentence modalityrecognition in French. In this work, only prosodic features are considered. The sentences are recognized according to the three following modalities: declarative, interrogative and exclamatory sentences. This information will be used to animate a talking head for deaf and hearingimpaired children. We first statistically study a real radio corpus in order to assess the feasibility of the automatic modeling of sentence types. Then, we test two sets of prosodicfeatures as well as two different classifiers and their combination. We further focus our attention on questions recognition, as this modality is certainly the most important one for the target application.

Keywords: prosody, fundamental frequency (F0), energy, automatic sentences modality recognition (ASMR), modal corpus

Year: 2005

Download:  Full text [49 kB]

Pavel Král

Phone: +420 377 632 454
E-mail: pkral@kiv,zcu.cz
WWW: http://home.zcu.cz/~pkral/

Pavel is a lecturer/researcher at the Department of Computer Science and Engineering at the University of West Bohemia in Pilsen (Czech Republic). His research is focused on automatic speech processing, dialog act recognition, syntactic parsing, punctuation annotation and document classification.

Jana Klečková

Christophe Cerisara