Speaker Identification in Network Environment
This paper is to identify a speaker in a networking environment. Automatic speaker identification is a fundamental task in speech processing. The proposed work is conducted in three phases: speech detection, clustering and speaker Identification. The process of capturing speech from a remote computer in an intranet environment involves recording huge volume of data or frames of speech. This is done by recording continuously the sound signals from the remote computer. The unwanted data in the recorded speech data is removed and the resultant data is taken to identification. MFCC technique is used for feature extraction and vector quantization is used for quantizing the features identified.