An analysis of prosodic information for the recognition of dialogue acts in a multimodal corpus in Mexican Spanish

Authors:
Sergio R. Coria;Luis A. Pineda
Affiliations:
Universidad Nacional Autónoma de México, Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Depto. de Ciencias Computacionales, Ciudad Universitaria, México, ...;Universidad Nacional Autónoma de México, Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Depto. de Ciencias Computacionales, Ciudad Universitaria, México, ...
Venue:
Computer Speech and Language
Year:
2009

Citing 9
Cited 0

Assessing agreement on classification tasks: the kappa statistic

Computational Linguistics
On Comparing Classifiers: Pitfalls toAvoid and a Recommended Approach

Data Mining and Knowledge Discovery
The DIME Project

MICAI '02 Proceedings of the Second Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence
Verbmobil - Translation of Face-To-Face Dialogs

Grundlagen und Anwendungen der Künstlichen Intelligenz, 17. Fachtagung für Künstliche Intelligenz, Humboldt-Universität zu
An architecture for a generic dialogue shell

Natural Language Engineering
Towards using prosody in speech recognition/understanding systems: differences between read and spontaneous speech

HLT '91 Proceedings of the workshop on Speech and Natural Language
Statistical Comparisons of Classifiers over Multiple Data Sets

The Journal of Machine Learning Research
Balancing transactions in practical dialogues

CICLing'06 Proceedings of the 7th international conference on Computational Linguistics and Intelligent Text Processing
Predicting dialogue acts from prosodic information

CICLing'06 Proceedings of the 7th international conference on Computational Linguistics and Intelligent Text Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents empirical results of an analysis on the role of prosody in the recognition of dialogue acts and utterance mood in a practical dialogue corpus in Mexican Spanish. The work is configured as a series of machine-learning experimental conditions in which models are created by using intonational and other data as predictors and dialogue act tagging data as targets. We show that utterance mood can be predicted from intonational information, and that this mood information can then be used to recognize the dialogue act.