International Journal of Advanced Engineering and Technology

International Journal of Advanced Engineering and Technology


International Journal of Advanced Engineering and Technology
International Journal of Advanced Engineering and Technology
Vol. 3, Issue 4 (2019)

Speaker identification using vector quantization and dynamic time warping


Pardeep Sangwan

Speaker Recognition is a system in which an individual is recognized based on voice signals. In this article, we provide a brief overview of the history of the methodology used in speech recognition for pattern identification. A method for modelling a speaker recognition system was also addressed and suggested, which involves the pre-processing stage, the extraction phase of features and the classification phase of patterns. LPCC and MFCC are used in this method as text-related speech recognition and the experiment uses vector quantization and dynamic time warping (DTW) to compare a speaking identity recognition rate for LPCC, MFCC or a combination of LPCC and MFCC. This reflects the higher acceptance levels for LPCC and MFCC.
Download  |  Pages : 54-55
How to cite this article:
Pardeep Sangwan. Speaker identification using vector quantization and dynamic time warping. International Journal of Advanced Engineering and Technology, Volume 3, Issue 4, 2019, Pages 54-55
International Journal of Advanced Engineering and Technology International Journal of Advanced Engineering and Technology