Feature selection for improved phone duration modeling of Greek emotional speech

This source preferred by Theodoros Kostoulas

This data was imported from DBLP:

Authors: Lazaridis, A., Ganchev, T., Mporas, I., Kostoulas, T. and Fakotakis, N.

Editors: Konstantopoulos, S., Perantonis, S.J., Karkaletsis, V., Spyropoulos, C.D. and Vouros, G.A.

https://doi.org/10.1007/978-3-642-12842-4

Volume: 6040

Pages: 357-362

Publisher: Springer

ISBN: 978-3-642-12841-7

This data was imported from Scopus:

Authors: Lazaridis, A., Ganchev, T., Mporas, I., Kostoulas, T. and Fakotakis, N.

Volume: 6040 LNAI

Pages: 357-362

ISBN: 9783642128417

DOI: 10.1007/978-3-642-12842-4_43

In the present work we address the problem of phone duration modeling for the needs of emotional speech synthesis. Specifically, relying on ten well known machine learning techniques, we investigate the practical usefulness of two feature selection techniques, namely the Relief and the Correlation-based Feature Selection (CFS) algorithms, for improving the accuracy of phone duration modeling. The feature selection is performed over a large set of phonetic, morphologic and syntactic features. In the experiments, we employed phone duration models, based on decision trees, linear regression, lazy-learning algorithms and meta-learning algorithms, trained on a Modern Greek speech database of emotional speech, which consists of five categories of emotional speech: anger, fear, joy, neutral, sadness. The experimental results demonstrated that feature selection significantly improves the accuracy of phone duration modeling regardless of the type of machine learning algorithm used for phone duration modeling. © Springer-Verlag Berlin Heidelberg 2010.

The data on this page was last updated at 04:57 on May 24, 2019.