Automatic Prominence Detection in Argentinian Spanish

Diego Evin, Christian Cossio-Mercado, Humberto Maximiliano Torres, Jorge Gurlekian, Hansjörg Mixdorff

Prominence is a perceptual attribute employed to communicate focus, contrasts and expressive nuances. This article explores the automatic detection of segments considered prominent by native listeners, using a corpus of Argentinean Spanish. The prominence detection is modeled as a binary classification problem over syllabic units. From perceptual assessments by a group of native listeners, we obtained a set of prominent syllable annotations, which are used as the gold standard to train and evaluate automatic classifiers. We study the performance of the classifiers under different sets of acoustic features, under various combinations of syllabic contexts, and using different classification algorithms. The best overall performance using leave-one speaker out cross validation had a mean precision rate of 94.75%, and was obtained using an SVM classifier, with two context syllables around each side of the central syllable, and applying the complete set of acoustic features considered.

 DOI: 10.21437/SpeechProsody.2018-138

Cite as: Evin, D., Cossio-Mercado, C., Torres, H.M., Gurlekian, J., Mixdorff, H. (2018) Automatic Prominence Detection in Argentinian Spanish. Proc. 9th International Conference on Speech Prosody 2018, 680-684, DOI: 10.21437/SpeechProsody.2018-138.

  author={Diego Evin and Christian Cossio-Mercado and Humberto Maximiliano Torres and Jorge Gurlekian and Hansjörg Mixdorff},
  title={Automatic Prominence Detection in Argentinian Spanish},
  booktitle={Proc. 9th International Conference on Speech Prosody 2018},