Automatic prosodic tone choice classification with Brazil’s intonation model

David O. Johnson, Okim Kang

Research output: Contribution to journalArticlepeer-review

11 Scopus citations


This paper examines the performance of automatically classifying five tone choices (i.e., falling, rising, rising-falling, falling-rising, and neutral) of Brazil’s intonation model. We tested two machine learning classifiers (neural network and boosting ensemble) in two configurations (multi-class and pairwise coupling) and a rule-based classifier. Three sets of acoustic features built from the TILT and Bézier pitch contour models and a new four-point pitch contour model we introduced here were investigated. Tone choices are one of the key elements of Brazil’s prosodic intonation model. We found the rule-based classifier, which was built on our four-point model, achieved better results than the others with an accuracy of 75.1 % and a Cohen’s kappa coefficient of 0.73. This research proves that it is possible to classify tone choices with an accuracy reaching close to the percentage of agreement between two human analysts. The findings further concluded that our four-point model was better for classifying Brazil’s tone choices than both of the TILT or Bézier models.

Original languageEnglish (US)
Pages (from-to)95-109
Number of pages15
JournalInternational Journal of Speech Technology
Issue number1
StatePublished - Mar 1 2016


  • Brazil’s prosodic intonation model
  • Bézier model
  • Machine learning
  • TILT model
  • ToBI
  • Tone choice classification

ASJC Scopus subject areas

  • Software
  • Language and Linguistics
  • Human-Computer Interaction
  • Linguistics and Language
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Automatic prosodic tone choice classification with Brazil’s intonation model'. Together they form a unique fingerprint.

Cite this