%N 6
%R 10.1016/j.jvoice.2015.08.010
%D 2016
%T Automatic Voice Pathology Detection With Running Speech by Using Estimation of Auditory Spectrum and Cepstral Coefficients Based on the All-Pole Model
%V 30
%O cited By 42
%K attention; classification; data base; ear; hearing; hospital; human; human experiment; model; pathology; psychophysics; running; speech; United States; voice; acoustics; algorithm; area under the curve; automated pattern recognition; factual database; Fourier analysis; pathophysiology; predictive value; procedures; receiver operating characteristic; reproducibility; signal processing; sound detection; speech analysis; statistical model; time factor; Voice Disorders, Acoustics; Algorithms; Area Under Curve; Databases, Factual; Fourier Analysis; Humans; Linear Models; Pattern Recognition, Automated; Predictive Value of Tests; Reproducibility of Results; ROC Curve; Signal Processing, Computer-Assisted; Sound Spectrography; Speech Acoustics; Speech Production Measurement; Time Factors; Voice Disorders; Voice Quality
%P 757.e7-757.e19
%L scholars6718
%I Mosby Inc.
%A Z. Ali
%A I. Elamvazuthi
%A M. Alsulaiman
%A G. Muhammad
%X Background and Objective Automatic voice pathology detection using sustained vowels has been widely explored. Because of the stationary nature of the speech waveform, pathology detection with a sustained vowel is a comparatively easier task than that using a running speech. Some disorder detection systems with running speech have also been developed, although most of them are based on a voice activity detection (VAD), that is, itself a challenging task. Pathology detection with running speech needs more investigation, and systems with good accuracy (ACC) are required. Furthermore, pathology classification systems with running speech have not received any attention from the research community. In this article, automatic pathology detection and classification systems are developed using text-dependent running speech without adding a VAD module. Method A set of three psychophysics conditions of hearing (critical band spectral estimation, equal loudness hearing curve, and the intensity loudness power law of hearing) is used to estimate the auditory spectrum. The auditory spectrum and all-pole models of the auditory spectrums are computed and analyzed and used in a Gaussian mixture model for an automatic decision. Results In the experiments using the Massachusetts Eye & Ear Infirmary database, an ACC of 99.56 is obtained for pathology detection, and an ACC of 93.33 is obtained for the pathology classification system. The results of the proposed systems outperform the existing running-speech�based systems. Discussion The developed system can effectively be used in voice pathology detection and classification systems, and the proposed features can visually differentiate between normal and pathological samples. © 2015 The Voice Foundation
%J Journal of Voice