Research Article Open Access

Comparison of Approaches for Predicting Break Indices in Mandarin Speech Synthesis

Shao Yan-qiu, Zhao Yong-zhen, Han Ji-qing and Liu Ting

Abstract

This study adopts a large-scale corpus with five-tier break indices annotated according to C-TOBI. Based on it, several approaches, N-gram, Markov model and decision tree learning are applied to predict break indices automatically for unrestricted mandarin text. These approaches differ mutually not only in model, but also on features and even part-of-speech tag size. A deep comparison and analysis among these approaches was made in the research.

Journal of Computer Science
Volume 2 No. 8, 2006, 660-664

DOI: https://doi.org/10.3844/jcssp.2006.660.664

Submitted On: 10 April 2006 Published On: 31 August 2006

How to Cite: Yan-qiu, S., Yong-zhen, Z., Ji-qing, H. & Ting, L. (2006). Comparison of Approaches for Predicting Break Indices in Mandarin Speech Synthesis. Journal of Computer Science, 2(8), 660-664. https://doi.org/10.3844/jcssp.2006.660.664

  • 2,964 Views
  • 2,260 Downloads
  • 1 Citations

Download

Keywords

  • Markov models
  • speech synthesis
  • break indices
  • n-gram
  • decision tree