Analysis of vocal disorders in a feature space

• Published in: 2000 10th European Signal Processing Conference 2000-07, Vol.22 (6), p.413-418
• Main Authors: Matassini, Lorenzo, Hegger, Rainer, Kantz, Holger, Manfredi, Claudia
• Format: Article
• Language: English
• Subjects: Algorithms; Autocorrelation functions; Bifurcation; Biological and medical sciences; Chaos; Classification; Diagnosis, Computer-Assisted - methods; Diseases; Disorders; Entropy; Humans; Indexes; Male; Mathematical analysis; Medical sciences; Models, Theoretical; Noise; Oscillations; Otorhinolaryngology (head neck, general aspects and miscellaneous); Otorhinolaryngology. Stomatology; Predictive Value of Tests; Separation; Severity of Illness Index; Signal Processing, Computer-Assisted; Speech; Speech Disorders - classification; Speech Disorders - diagnosis; Speech Disorders - physiopathology; Tumors; Vectors; Vectors (mathematics); Vocal Cords - physiopathology; Vocal Cords - surgery; Voice Disorders - classification; Voice Disorders - diagnosis; Voice Disorders - physiopathology
• ISSN: 1350-4533; 1873-4030
• DOI: 10.1016/S1350-4533(00)00048-5

This paper provides a way to classify vocal disorders for clinical applications. This goal is achieved by means of geometric signal separation in a feature space. Typical quantities from chaos theory (like entropy, correlation dimension and first lyapunov exponent) and some conventional ones (like autocorrelation and spectral factor) are analysed and evaluated, in order to provide entries for the feature vectors. A way of quantifying the amount of disorder is proposed by means of a healthy index that measures the distance of a voice sample from the centre of mass of both healthy and sick clusters in the feature space. A successful application of the geometrical signal separation is reported, concerning distinction between normal and disordered phonation.