ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Exploring automatic similarity measures for unit selection tuning

Daniel Tihelka, Jan Romportl

The present paper focuses on the current handling of target features in the unit selection approach basically requiring huge corpora. In the paper there are outlined possible solutions based on measuring (dis)similarity among prosodic patterns. As the start of research, the feasibility of (dis)similarity estimation is examined on several intuitively chosen measures of acoustic signal which are correlated to perceived similarity obtained from a large-scale listening test.


doi: 10.21437/Interspeech.2009-250

Cite as: Tihelka, D., Romportl, J. (2009) Exploring automatic similarity measures for unit selection tuning. Proc. Interspeech 2009, 736-739, doi: 10.21437/Interspeech.2009-250

@inproceedings{tihelka09_interspeech,
  author={Daniel Tihelka and Jan Romportl},
  title={{Exploring automatic similarity measures for unit selection tuning}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={736--739},
  doi={10.21437/Interspeech.2009-250}
}