Authors:
Abdenour Hacine-Gharbi
1
;
Mélanie Petit
2
;
Philippe Ravier
2
and
François Némo
2
Affiliations:
1
University of Bordj Bou Arreridj, Algeria and University of Orleans, France
;
2
University of Orléans, France
Keyword(s):
Intonation Classification, HMM, Prosodic Features, Reduction Dimensionality, Curse of Dimensionality, Wrappers Feature Selection, Categorization of Word’s Uses.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Artificial Intelligence
;
Audio and Speech Processing
;
Classification
;
Digital Signal Processing
;
Feature Selection and Extraction
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Multimedia
;
Multimedia Signal Processing
;
Natural Language Processing
;
Pattern Recognition
;
Software Engineering
;
Symbolic Systems
;
Telecommunications
;
Theory and Methods
Abstract:
When working with oral speech, the issue of natural meaning processing can be improved using easily available prosodic information. Only recently, semanticists have started to consider that the prosodic features could play a key role in the interpretation and classification of different word’s uses. In this work, we propose a prosodic based automatic system that allows to classify the French word ‘oui’ into one of the classes ‘conviction’ or ‘lack of conviction’. To that aim, a questionnaire inspired from opinion polls has been created and permitted to obtain 118 occurrences for both classes of ‘oui’. Combined with feature selection procedure, the best classification rates decreases from 85.45% (speaker dependent mode) to 79.25% (speaker independent mode which is closer to an application). Interestingly, we also introduce the ‘shuttle’ principle that seeks to validate the semantic interpretation thanks to prosodic analysis.