Multidirectional Regression (MDR)-Based Features for Automatic Voice Disorder Detection

作者：Muhammad Ghulam^*; Mesallam Tamer A; Malki Khalid H; Farahat Mohamed; Mahmood Awais; Alsulaiman Mansour

来源：Journal of Voice, 2012, 26(6): 817.e19.

DOI：10.1016/j.jvoice.2012.05.002

• Voice disorders detection
• Multidirectional regression
• Automatic speech recognition
• Arabic digits

Background and Objective. Objective assessment of voice pathology has a growing interest nowadays. Automatic speech/speaker recognition (ASR) systems are commonly deployed in voice pathology detection. The aim of this work was to develop a novel feature extraction method for ASR that incorporates distributions of voiced and unvoiced parts, and voice onset and offset characteristics in a time-frequency domain to detect voice pathology. %26lt;br%26gt;Materials and Methods. The speech samples of 70 dysphonic patients with six different types of voice disorders and 50 normal subjects were analyzed. The Arabic spoken digits (1-10) were taken as an input. The proposed feature extraction method was embedded into the ASR system with Gaussian mixture model (GMM) classifier to detect voice disorder. %26lt;br%26gt;Results. Accuracy of 97.48% was obtained in text independent (all digits%26apos; training) case, and over 99% accuracy was obtained in text dependent (separate digit%26apos;s training) case. The proposed method outperformed the conventional Mel frequency cepstral coefficient (MFCC) features. %26lt;br%26gt;Conclusion. The results of this study revealed that incorporating voice onset and offset information leads to efficient automatic voice disordered detection.

• 出版日期2012-11