Share Email Print

Proceedings Paper

Automatic feature template generation for maximum entropy based intonational phrase break prediction
Author(s): You Zhou
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The prediction of intonational phrase (IP) breaks is important for both the naturalness and intelligibility of Text-to- Speech (TTS) systems. In this paper, we propose a maximum entropy (ME) model to predict IP breaks from unrestricted text, and evaluate various keyword selection approaches in different domains. Furthermore, we design a hierarchical clustering algorithm for automatic generation of feature templates, which minimizes the need for human supervision during ME model training. Results of comparative experiments show that, for the task of IP break prediction, ME model obviously outperforms classification and regression tree (CART), log-likelihood ratio is the best scoring measure of keyword selection, compared with manual templates, templates automatically generated by our approach greatly improves the F-score of ME based IP break prediction, and significantly reduces the size of ME model.

Paper Details

Date Published: 14 March 2013
PDF: 6 pages
Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87681H (14 March 2013); doi: 10.1117/12.2010767
Show Author Affiliations
You Zhou, Hunan Univ. of Finance and Economics (China)

Published in SPIE Proceedings Vol. 8768:
International Conference on Graphic and Image Processing (ICGIP 2012)
Zeng Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top