Speaker identification using usable speech concept
Ananth N. Iyer, Brett Y. Smolenski, Robert E. Yantorno, Jashmin K Shah, Edward J. Cupples, Stanley J. Wenndt · European Signal Processing Conference · 2004
Most signal processing involves processing a signal without concern for the quality or information content of that signal. In speech processing, speech is processed on a frameby-frame basis, usually only with concern that the frame is either speech or silence. However, knowing how reliable the information is in a frame of speech can be very important and useful. This is where usable speech detection and extraction can play a very important role. The usable speech frames can be defined as frames of speech that contain higher information content compared to unusable frames with reference to a particular application. We have been investigating a speaker identification system to identify usable speech frames and then to determine a method for identifying those frames as usable using a different approach. A 100% accuracy can be achieved in speaker identification by using only the extracted usable speech segments.