relation: https://khub.utp.edu.my/scholars/4497/ title: Voice pathology detection using auto-correlation of different filters bank creator: Al-Nasheri, A. creator: Ali, Z. creator: Muhammad, G. creator: Alsulaiman, M. description: This paper investigates the contribution of frequency bands for automatic voice pathology detection. First, the input voice signal is passed through a number of time-domain band-pass filters. The center frequencies are spaced on an octave scale. Each filter output is then divided into overlapping frames. Auto-correlation function is applied to each block to find the first largest peak, in areas other than near the dc value, and its corresponding lag. Therefore, each frame is having only these two features (peak value and lag). As classifier, we use Gaussian mixture models (GMM) and support vector machine (SVM), separately. Two well-known available databases, one in English (MEEI) and the other one in German (SVD), are used in the investigation. The results demonstrate that the most significant frequency range to detect voice pathology is between 1500 Hz and 3500 Hz. Using this filter band and with only two features, the accuracy is above 97 in case of the MEEI database. © 2014 IEEE. publisher: IEEE Computer Society date: 2014 type: Conference or Workshop Item type: PeerReviewed identifier: Al-Nasheri, A. and Ali, Z. and Muhammad, G. and Alsulaiman, M. (2014) Voice pathology detection using auto-correlation of different filters bank. In: UNSPECIFIED. relation: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84988239949&doi=10.1109%2fAICCSA.2014.7073178&partnerID=40&md5=bdedcb6044c0a83f39809c9ca544c2b2 relation: 10.1109/AICCSA.2014.7073178 identifier: 10.1109/AICCSA.2014.7073178