ISCA Archive Eurospeech 1999
ISCA Archive Eurospeech 1999

Modelling intonational phrase structure with artificial neural networks

Grazyna Demenko, Wiktor Jassem

A model of intonation for Polish has been created on the basis of a general theory of suprasegmentals and on experiments using isolated utterances as well as continuous speech. An intonational phrase consists of an optional prenuclear tune and an obligatory nuclear tune. A training of a three-layer MLP network was performed distinguishing 9 nuclear accents: HL, ML, LL, HM, LH, LM, MH, MM, LHL and 2 secondary prenuclear accents: High (H) and Low (L). A total of 1600 structures (in constructed phrases) were used for training, and 430 for verification. The average score for training and testing was 82 percent. In continuous speech the following structures were postulated: H and L for prenuclear intonation and for nuclear intonations: R (rising), F (falling), MM (level), LHL (rising-falling). For the testing set, a score between 79 and 83 per cent was obtained. In both classifications, an 11-element vector was used to describe the intonational structures under analysis.


doi: 10.21437/Eurospeech.1999-172

Cite as: Demenko, G., Jassem, W. (1999) Modelling intonational phrase structure with artificial neural networks. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 711-714, doi: 10.21437/Eurospeech.1999-172

@inproceedings{demenko99_eurospeech,
  author={Grazyna Demenko and Wiktor Jassem},
  title={{Modelling intonational phrase structure with artificial neural networks}},
  year=1999,
  booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
  pages={711--714},
  doi={10.21437/Eurospeech.1999-172}
}