Quantitative Assessment of Speech in Cerebellar Ataxia Using Magnitude and Phase Based Cepstrum

Bipasha Kashyap, Pubudu N. Pathirana, Malcolm Horne, Laura Power, David Szmulewicz

Research output: Contribution to journalArticleResearchpeer-review

16 Citations (Scopus)

Abstract

The clinical assessment of speech abnormalities in Cerebellar Ataxia (CA) is time-consuming and inconsistent. We have developed an automated objective system to quantify CA severity and thereby facilitate remote monitoring and optimisation of therapeutic interventions. A quantitative acoustic assessment could prove to be a viable biomarker for this purpose. Our study explores the use of phase-based cepstral features extracted from the modified group delay function as a complement to the features obtained from the magnitude cepstrum. We selected a combination of 15 acoustic measurements using RELIEF feature selection algorithm during the feature optimisation process. These features were used to segregate ataxic speakers from normal speakers (controls) and objectively assess them based on their severity. The effectiveness of our study has been experimentally evaluated through a clinical study involving 42 patients diagnosed with CA and 23 age-matched controls. A radial basis function kernel based support vector machine (SVM) classifier achieved a classification accuracy of 84.6% in CA–Control discrimination [area under the ROC curve (AUC) of 0.97] and 74% in the modified 3-level CA severity estimation (AUC of 0.90) deduced from the clinical ratings. The strong classification ability of selected features and the SVM model supports this scheme’s suitability for monitoring CA related speech motor abnormalities.

Original languageEnglish
Pages (from-to)1322-1336
Number of pages15
JournalAnnals of Biomedical Engineering
Volume48
Issue number4
DOIs
Publication statusPublished - 1 Apr 2020
Externally publishedYes

Keywords

  • Cepstrum
  • Feature selection
  • Mel-frequency cepstral coefficients (MFCCs)
  • Modified group delay (MGD)
  • Phase
  • Random Forests (RF)
  • Support vector machines (SVM)

Cite this