ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Identification and automatic detection of parasitic speech sounds

Jindřich Matoušek, Radek Skarnitzl, Pavel Machač, Jan Trmal

This paper presents initial experiments with the identification and automatic detection of parasitic sounds in speech signals. The main goal of this study is to identify such sounds in the source recordings for unit-selection-based speech synthesis systems and thus to avoid their unintended usage in synthesised speech. The first part of the paper describes the phonetic analysis and identification of parasitic phenomena in recordings of two Czech speakers. In the second part, experiments with the automatic detection of parasitic sounds using HMM-based and BVM classifiers are presented. The results are encouraging, especially those for glottalization phenomena.


doi: 10.21437/Interspeech.2009-265

Cite as: Matoušek, J., Skarnitzl, R., Machač, P., Trmal, J. (2009) Identification and automatic detection of parasitic speech sounds. Proc. Interspeech 2009, 876-879, doi: 10.21437/Interspeech.2009-265

@inproceedings{matousek09_interspeech,
  author={Jindřich Matoušek and Radek Skarnitzl and Pavel Machač and Jan Trmal},
  title={{Identification and automatic detection of parasitic speech sounds}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={876--879},
  doi={10.21437/Interspeech.2009-265}
}