A Review and Analysis of Voice Identification System

  • Pharindra Kumar Sharma Scholar, Computer Science and Engineering, Noida International University, Noida, India
  • Neeraj Sahu Asst. Professor MANIT, Bhopal, India
Keywords: MFCC;Knn;Distance;Voice Signal


Identifying a voice of a person by own voice is a very important human peculiarity, in order that a human easily recognize. The too many subjective problems are arrived in voice identification in compare of noisy voice, very low quality voice, mixing voice and etc.  In this article, we are studies some of voice identification methods with their result accuracy. We know that, the voice identification have two main parts, one part explain the extraction of voice signals by MFCC, adaptive MFCC, Cepstral mean subtraction Robust Feature extraction method. The next part, find the similarity of extracted voice signals by some prominent methods like kNN with Double distance method, deep learning method, pattern identification method and etc.

We conclude this review with a analysis of method of human voice identification and have a go at to point out strengths and weaknesses of methods.


1. Becker, S., et al. (2009). "Flow-structure-acoustic interaction in a human voice model." The Journal of the Acoustical Society of America 125(3): 1351-1361.
2. Evans, S., et al. (2006). "Relationships between vocal characteristics and body size and shape in human males: an evolutionary explanation for a deep male voice." Biological psychology 72(2): 160-163.
3. Parasuraman, R., et al. (2000). "A model for types and levels of human interaction with automation." IEEE Transactions on systems, man, and cybernetics-Part A: Systems and Humans 30(3): 286-297.
4. Muda, L., et al. (2010). "Voice identification algorithms using mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques." arXiv preprint arXiv:1003.4083.
5. Ranny, "Voice identification using k nearest neighbor and double distance method", 2016 International Conference on Industrial Engineering Management Science and Application (ICIMSA), pp. 1-5, May 2016.