Abstract:

                     Speaker recognition is the process of determining which registered speaker provides a given utterance followed by the process of accepting or rejecting the identity claim of a speaker. This paper reports on an experimental study involving signal processing in both time and frequency domain, and to receive a small bit of insight into the principles of speech analysis. This was accomplished by recording four speech segments from each person in our classroom, all of them varying slightly. Comparisons and analysis were then made on each signal, depending upon the instructions given by Dr. Qi.

Key words: Degradation, Pitch, Formant, Enhancement