Zulfiqar Ali1, Irraivan Elamvazuthi2, Mansour Alsulaiman3, Ghulam Muhammad3. 1. Centre for Intelligent Signal and Imaging Research, Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Tronoh 31750, Perak, Malaysia; Digital Speech Processing Group, Department of Computer Engineering, King Saud University, Riyadh 11543, Saudi Arabia. Electronic address: zulfiqar_g02579@utp.edu.my. 2. Centre for Intelligent Signal and Imaging Research, Department of Electrical and Electronic Engineering, Universiti Teknologi PETRONAS, Tronoh 31750, Perak, Malaysia. 3. Digital Speech Processing Group, Department of Computer Engineering, King Saud University, Riyadh 11543, Saudi Arabia.
Abstract
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. Copyright Â
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. Copyright Â
Authors: Javier Andreu-Perez; Humberto Perez-Espinosa; Eva Timonet; Mehrin Kiani; Manuel I Giron-Perez; Alma B Benitez-Trinidad; Delaram Jarchi; Alejandro Rosales-Perez; Nick Gatzoulis; Orion F Reyes-Galaviz; Alejandro Torres-Garcia; Carlos A Reyes-Garcia; Zulfiqar Ali; Francisco Rivas Journal: IEEE Trans Serv Comput Date: 2021-02-23 Impact factor: 11.019