Objective Severity Assessment from Disordered Voice Using Estimated Glottal Airflow

Yu-Ren Chien, Michal Borský, Jón Guðnason


In clinical practice, the severity of disordered voice is typically rated by a professional with auditory-perceptual judgment. The present study aims to automate this assessment procedure, in an attempt to make the assessment objective and less labor-intensive. In the automated analysis, glottal airflow is estimated from the analyzed voice signal with an inverse filtering algorithm. Automatic assessment is realized by a regressor that predicts from temporal and spectral features of the glottal airflow. A regressor trained on overtone amplitudes and harmonic richness factors extracted from a set of continuous-speech utterances was applied to a set of sustained-vowel utterances, giving severity predictions (on a scale of ratings from 0 to 100) with an average error magnitude of 14.


 DOI: 10.21437/Interspeech.2017-138

Cite as: Chien, Y., Borský, M., Guðnason, J. (2017) Objective Severity Assessment from Disordered Voice Using Estimated Glottal Airflow. Proc. Interspeech 2017, 304-308, DOI: 10.21437/Interspeech.2017-138.


@inproceedings{Chien2017,
  author={Yu-Ren Chien and Michal Borský and Jón Guðnason},
  title={Objective Severity Assessment from Disordered Voice Using Estimated Glottal Airflow},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={304--308},
  doi={10.21437/Interspeech.2017-138},
  url={http://dx.doi.org/10.21437/Interspeech.2017-138}
}