Call for Paper - January 2024 Edition
IJCA solicits original research papers for the January 2024 Edition. Last date of manuscript submission is December 20, 2023. Read More

Inverted Mel Feature Set based Text-Independent Speaker Identification using Finite Doubly Truncated Gaussian Mixture Model

Print
PDF
 
Download Full Text
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 156 - Number 2
Year of Publication: 2016
Authors:
V. Sailaja, P. Sunitha, B. Vasantha Lakshmi
10.5120/ijca2016912369

V Sailaja, P Sunitha and Vasantha B Lakshmi. Inverted Mel Feature Set based Text-Independent Speaker Identification using Finite Doubly Truncated Gaussian Mixture Model. International Journal of Computer Applications 156(2):14-16, December 2016. BibTeX

@article{10.5120/ijca2016912369,
	author = {V. Sailaja and P. Sunitha and B. Vasantha Lakshmi},
	title = {Inverted Mel Feature Set based Text-Independent Speaker Identification using Finite Doubly Truncated Gaussian Mixture Model},
	journal = {International Journal of Computer Applications},
	issue_date = {December 2016},
	volume = {156},
	number = {2},
	month = {Dec},
	year = {2016},
	issn = {0975-8887},
	pages = {14-16},
	numpages = {3},
	url = {http://www.ijcaonline.org/archives/volume156/number2/26680-2016912369},
	doi = {10.5120/ijca2016912369},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

This paper provides an efficient approach for text-independent speaker identification using the Inverted Mel-frequency Cepstral Coefficients as feature set and Finite Doubly Truncated Gaussian Mixture as Model (FDTGMM). Over the years, Mel-Frequency Cepstral Coefficients (MFCC), modeled on the human auditory system, has been used as a standard acoustic feature set for speech related applications. Furthermore, it has been shown that the Inverted Mel-frequency Cepstral Coefficients (IMFCC) is also a useful feature set for Speaker identification, which contains information complementary to MFCC as, it covers high frequency region more closely. The performance of the developed model is studied through experimental evaluation with 45 speaker’s data base and identification accuracy.

References

  1. Douglas A. Reynolds, Richard C. Rose, “Robust Text-Independent Speaker Identification Using Gaussian Mixture Models” , IEEE Trans. on Speech and Audio Processing, January 1995, Vol. 3, No. 1, pp72-82.
  2. Herbert Gish, Michael Schmidt, Text Independent Speaker Identification, IEEE Signal Processing Magazine, Oct 1994.
  3. Ruchi Chaudhary “Performance study of Text-independent Speaker identification system using MFCC & IMFCC for Telephone and Microphone Speeches” International Journal of Computing and Business Research (IJCBR) ,ISSN (Online) : 2229-6166, Volume 3 Issue 2 May 2012 pp.1-11.
  4. R.Shantha Selva Kumari , S. Selva Nidhyananthan , Anand.G “Fused Mel Feature sets based Text-Independent Speaker Identification using Gaussian Mixture Mode” International Conference on Communication Technology and System Design 2011, Procedia Engineering 30 ( 2012 ) pp. 319 – 326
  5. Cohen A.C. Jr. “Estimating the Mean and Variance of Normal Populations from Singly and Doubly Truncated Samples”, Ann.Maths. Statist., 21, pp 557-569.1950.
  6. V Sailaja , K Srinivasa Rao & K V V S Reddy “Text Independent Speaker Identification Using Finite Doubly Truncated Gaussian Mixture Model”, International Journal of Information Technology and Knowledge Management July-December 2010, Volume 2, No. 2, pp. 475-480.

Keywords

Speaker Identification, IMFCC, FDTGMM, Identification accuracy.