Speaker identification improvement using the usable speech concept
A. N. Iyer, Brett Y. Smolenski, Robert E. Yantorno, Jashmin K Shah, Edward J. Cupples, Stanley J. Wenndt · 2004
Most signal processing involves processing a signal with-out concern for the quality or information content of that signal. In speech processing, speech is processed on a frame-by-frame basis, usually only with concern that the frame is either speech or silence. However, knowing how reli-able the information is in a frame of speech can be very important and useful. This is where usable speech detec-tion and extraction can play a very important role. The us-able 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 iden-tify usable speech frames and then to determine a method for identifying those frames as usable using a different ap-proach. A 100 % accuracy can be achieved in speaker identi-fication by using only the extracted usable speech segments. 1.