Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/27819
Author(s): | Medeiros, H. Moniz, H. Batista, F. Trancoso, I. Nunes, L. |
Editor: | Bimbot, F., Cerisara, C., Fougeron, C., Gravier, G., Lamel, L., Pellegrino, F., and Perrier, P. |
Date: | 2013 |
Title: | Disfluency detection based on prosodic features for university lectures |
Volume: | 4 |
Book title/volume: | Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013) |
Pages: | 2629 - 2633 |
Event title: | 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013) |
Reference: | Medeiros, H., Moniz, H., Batista, F., Tjalve, M., Trancoso, I., & Nunes, L. (2013). Disfluency detection based on prosodic features for university lectures. In F. Bimbot, C. Cerisara, C. Fougeron, G. Gravier, L. Lamel, F. Pellegrino, & P. Perrier (Eds.), Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH 2013) (vol. 4, pp. 2629-2633). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2013-605 |
ISSN: | 2308-457X |
ISBN: | 978-1-62993-443-3 |
DOI (Digital Object Identifier): | 10.21437/Interspeech.2013-605 |
Keywords: | Prosodic features Automatic disfluency detection Corpus of university lectures Machine learning |
Abstract: | This paper focuses on the identification of disfluent sequences and their distinct structural regions, based on acoustic and prosodic features. Reported experiments are based on a corpus of university lectures in European Portuguese, with roughly 32h, and a relatively high percentage of disfluencies (7.6%). The set of features automatically extracted from the corpus proved to be discriminant of the regions contained in the production of a disfluency. Several machine learning methods have been applied, but the best results were achieved using Classification and Regression Trees (CART). The set of features which was most informative for cross-region identification encompasses word duration ratios, word confidence score, silent ratios, and pitch and energy slopes. Features such as the number of phones and syllables per word proved to be more useful for the identification of the interregnum, whereas energy slopes were most suited for identifying the interruption point. |
Peerreviewed: | yes |
Access type: | Open Access |
Appears in Collections: | ISTAR-CRI - Comunicações a conferências internacionais IT-CRI - Comunicações a conferências internacionais |
Files in This Item:
File | Size | Format | |
---|---|---|---|
conferenceobject_42668.pdf | 219,68 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.