CFP last date
20 May 2024
Reseach Article

Comparison of VQ and GMM for Text Independent Speaker Identification System for The Bengali Language

by Md Mahadi Hasan Nahid, Md Ashraful Islam, Md Saiful Islam
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 178 - Number 47
Year of Publication: 2019
Authors: Md Mahadi Hasan Nahid, Md Ashraful Islam, Md Saiful Islam
10.5120/ijca2019919354

Md Mahadi Hasan Nahid, Md Ashraful Islam, Md Saiful Islam . Comparison of VQ and GMM for Text Independent Speaker Identification System for The Bengali Language. International Journal of Computer Applications. 178, 47 ( Sep 2019), 18-21. DOI=10.5120/ijca2019919354

@article{ 10.5120/ijca2019919354,
author = { Md Mahadi Hasan Nahid, Md Ashraful Islam, Md Saiful Islam },
title = { Comparison of VQ and GMM for Text Independent Speaker Identification System for The Bengali Language },
journal = { International Journal of Computer Applications },
issue_date = { Sep 2019 },
volume = { 178 },
number = { 47 },
month = { Sep },
year = { 2019 },
issn = { 0975-8887 },
pages = { 18-21 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume178/number47/30866-2019919354/ },
doi = { 10.5120/ijca2019919354 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:53:21.594527+05:30
%A Md Mahadi Hasan Nahid
%A Md Ashraful Islam
%A Md Saiful Islam
%T Comparison of VQ and GMM for Text Independent Speaker Identification System for The Bengali Language
%J International Journal of Computer Applications
%@ 0975-8887
%V 178
%N 47
%P 18-21
%D 2019
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Speaker identification (SI) is the system to identify the person by the signal pattern of their voices. In recent years, many speaker identification models are proposed, but till now speaker identification technology do not reach their full potential. This paper presents a comprehensive comparative study of VQ and GMM to identify the speaker who speaks in Bengali accent. We consider the problem of text-independent speaker identification. We compare the performance/accuracy of VQ and GMM based Speaker Identification System (SIS). We use Mel Frequency Cepstral Coefficients (MFCC) and Liner Predictive Coding Coefficients (LPCC) for feature extraction.

References
  1. Ling Feng, "Speaker Recognition", IMM-THESIS: ISSN 1601-233X, Kgs. Lyngby 2004
  2. G. Saha, Sandipan Chakroborty, Suman Senapati, “A New Silence Removal and Endpoint Detection Algorithm for Speech and Speaker Recognition Applications” Department of Electronics and Electrical Communication Engineering Indian Institute of Technology, Khragpur, Kharagpur-721 302, India
  3. Yuan Yujin, Zhao Peihua, Zhou Qun,, “Research of speaker recognition based on combination of LPCC and MFCC”, Intelligent Computing and Intelligent Systems (ICIS), IEEE International Conference , vol.3, 29-31 Oct. 2010, pp.765-767. Reynolds, A.D., and Rose, C.R.: “Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models”. IEEE Transactions on Speech and Audio Processing, 3(1): 72-83, 1995.
  4. Ningping Fan, Justinian Rosca, "Enhanced VQ-based Algorithms for Speech Independent Speaker Identification", Siemens Corporate Research Inc., 755 College Road East, Princeton, New Jersey 08540
  5. Douglas Reynolds, "Gaussian Mixture Models" MIT Lincoln Laboratory, 244 Wood St., Lexington, MA 02140, USA.
  6. M.Campbell, D. E. Sturim, D. A. Reynolds: “Support Vector Machines using GMM Super vectors for Speaker Verification”, MIT Lincoln Laboratory.
  7. Tomi Kinnunen, Teemu Kilpeläinen And Pasi Fränti "Comparison Of Clustering Algorithms In Speaker Identification", Department Of Computer Science, University Of Joensuu, P.O.Box 111, 80101 Joensuu, Finland.
  8. Lindasalwa Muda, Mumtaj Begam and I. Elamvazuthi, "Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques", JOURNAL OF COMPUTING, VOLUME 2, ISSUE 3, MARCH 2010, ISSN 2151-9617
  9. Evgeny Karpov, "Real-Time Speaker Identification”, Master’s Thesis, Department of Computer Science, University of Joensuu, Finland, 2003
  10. Lindasalwa Muda, Mumtaj Begam and I. Elamvazuthi, "Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques", JOURNAL OF COMPUTING, VOLUME 2, ISSUE 3, MARCH 2010, ISSN 2151-9617
  11. Kim, Taesun, and Chulhun Seo. "A novel photonic bandgap structure for low-pass filter of wide stopband." IEEE Microwave and Guided Wave Letters 10.1 (2000): 13-15.
  12. Han, W., Chan, C. F., Choy, C. S., & Pun, K. P. (2006, May). An efficient MFCC extraction method in speech recognition. In 2006 IEEE international symposium on circuits and systems (pp. 4-pp). IEEE.
  13. MacLean, K. Voxforge. Ken MacLean. [Online]. Available: http://www. voxforge. org/home. [Acedido em 2016].
  14. Nahid, Md Mahadi Hasan, et al. "Comprehending Real Numbers: Development of Bengali Real Number Speech Corpus." arXiv preprint arXiv:1803.10136 (2018).
Index Terms

Computer Science
Information Sciences

Keywords

Bengali Speaker Identification SI Voice Recognition MFCC LPCC VQ GMM.