Using modulation spectra for voice pathology detection and classification
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. iv (1094687X) , 2514-2517
Abstract
In this paper, we consider the use of Modulation Spectra for voice pathology detection and classification. To reduce the high-dimensionality space generated by Modulation spectra we suggest the use of Higher Order Singular Value Decomposition (SVD) and we propose a feature selection algorithm based on the Mutual Information between subjective voice quality and computed features. Using SVM with a radial basis function (RBF) kernel as classifier, we conducted experiments on a database of sustained vowel recordings from healthy and pathological voices. For voice pathology detection, the suggested approach achieved a detection rate of 94.1% and an Area Under the Curve (AUC) score of 97.8%. For voice pathology classification, an average detection rate and AUC of 88.6% and 94.8%, respectively, was achieved in classifying polyp against keratosis leukoplakia, adductor spasmodic dysphonia and vocal nodules.Keywords
This publication has 14 references indexed in Scilit:
- Local Discriminant Wavelet Packet Basis for Voice Pathology Classification2008
- Feasibility of Single Channel Speaker Separation Based on Modulation Frequency Analysis2007
- Dimensionality Reduction of a Pathological Voice Quality Assessment System Based on Gaussian Mixture Models and Short-Term Cepstral ParametersIEEE Transactions on Biomedical Engineering, 2006
- Joint Acoustic-Modulation Frequency for Speaker Recognition2006
- Discrimination of Pathological Voices Using a Time-Frequency ApproachIEEE Transactions on Biomedical Engineering, 2005
- Automatic Detection of Voice Impairments by Means of Short-Term Cepstral Parameters and Neural Network Based DetectorsIEEE Transactions on Biomedical Engineering, 2004
- Joint Acoustic and Modulation FrequencyEURASIP Journal on Advances in Signal Processing, 2003
- Identification of Pathological Voices Using Glottal Noise MeasuresJournal of Speech, Language, and Hearing Research, 2000
- A Multilinear Singular Value DecompositionSIAM Journal on Matrix Analysis and Applications, 2000
- Should recognizers have ears?Speech Communication, 1998