Speaker identification system using pitch and formant analysis

Vinod Patil., Ankit Anand and Rahul Goyal

The aim of this paper is to design a Speaker Identification system using speech features like formant and pitch analysis. The pitch and formants are first extracted from the speech signal and then their analysis is carried out to recognize different emotional states of the person like happy, sad and neutral. Here we have used Cepstral Analysis Method for pitch extraction and LPC Method for formant extraction.

Download PDF: