Detection of Vocal Fold Paralysis and Edema Using Linear Discriminant Classifiers
In this paper, a two-class pattern recognition problem is studied, namely the automatic detection of speech disorders such as vocal fold paralysis and edema by processing the speech signal recorded from patients affected by the aforementioned pathologies as well as speakers unaffected by these pathologies. The data used were extracted from the Massachusetts Eye and Ear Infirmary database of disordered speech. The linear prediction coefficients are used as input to the pattern recognition problem. Two techniques are developed. The first technique is an optimal linear classifier design, while the second one is based on the dual-space linear discriminant analysis. Two experiments were conducted in order to assess the performance of the techniques developed namely the detection of vocal fold paralysis for male speakers and the detection of vocal fold edema for female speakers. Receiver operating characteristic curves are presented. Long-term mean feature vectors are proven very efficient in detecting the voice disorders yielding a probability of detection that may approach 100% for a probability of false alarm equal to 9.52%.
KeywordsFeature Vector False Alarm Receiver Operating Characteristic Curve Linear Discriminant Analysis Rectangular Window
Unable to display preview. Download preview PDF.
- 1.Quek, F., Harper, M., Haciahmetoglou, Y., Chen, L., Ramig, L.O.: Speech pauses and gestural holds in Parkinson ’s Disease. In: Proc. 2002 Int. Conf. Spoken Language Processing, pp. 2485–2488 (2002)Google Scholar
- 2.Will, L., Ramig, L.O., Spielman, J.L.: Application of Lee Silverman Voice Treatment (LSVT) to individuals with multiple sclerosis, ataxic dysarthria, and stroke. In: Proc. 2002 Int. Conf. Spoken Language Processing, pp. 2497–2500 (2002)Google Scholar
- 3.Spielman, J.L., Ramig, L.O., Borod, J.C.: Oro-facial changes in Parkinson’s Disease following intensive voice therapy (LSVT). In: Proc. 2002 Int. Conf. Spoken Language Processing, pp. 2489–2492 (2002)Google Scholar
- 7.Dibazar, A.A., Narayanan, S., Berger, T.W.: Feature analysis for automatic detection of pathological speech. In: Proc. Engineering Medicine and Biology Symposium 2002, vol. 1, pp. 182–183 (2002)Google Scholar
- 9.Marinaki, M., Kotropoulos, C., Pitas, I., Maglaveras, N.: Automatic detection of vocal fold paralysis and edema. In: Proc. 2004 Int. Conf. Spoken Language Processing (2004)Google Scholar
- 10.Nayak, J., Bhat, P.S.: Identification of voice disorders using speech samples. In: Proc. IEEE TenCon 2003, vol. 395 (2003)Google Scholar
- 11.Gómez, P., Godino, J.I., Rodríguez, F., Díaz, F., Nieto, V., Álvarez, A., Rodellar, V.: Evidence of vocal cord pathology from the mucosal wave cepstral contents. In: Proc. 2004 IEEE Int. Conf. Acoustics, Speech, and Signal Processing, vol. 5, pp. 437–440 (2004)Google Scholar
- 13.Tang, X., Wang, W.: Dual space linear discriminant analysis for face recognition. In: Proc. 2004 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, pp. 1064–1068 (2004)Google Scholar
- 14.Voice and Speech Laboratory, Massachusetts Eye and Ear Infirmary, Boston MA, Voice Disorders Database, 1.03 edition, Kay Elemetrics Corp. (1994)Google Scholar
- 15.Deller, J.R., Proakis, J.G., Hansen, J.H.L.: Discrete Time Processing of Speech Signals. MacMillan Publishing Company, NY (1993)Google Scholar