| In an operational environment speech is degraded by many kinds of interferences. The operations of many speech processing techniques are plagued by such interferences. Usable speech extraction is a concept of processing degraded speech data. The idea of usable speech is to identify and extract portions of degraded speech that are considered useful for various speech processing systems. The performance reduction of speaker identification systems under degraded conditions and use of usable speech concept to improve the performance has been demonstrated by previous work.;A new usable speech measure, based on the structure of Linear Predictive Coding (LPC) residual is developed to identify usable speech frames. It is shown that the method has success rate of 70% and false alarm rate of 34%. |
