MFCC based performance analysis of VQ and GMM Speaker identification system

Volume 5, Issue 4, August 2020     |     PP. 89-99      |     PDF (407 K)    |     Pub. Date: August 12, 2020
DOI:    220 Downloads     3117 Views  

Author(s)

Chandar Kumar, Faculty of Engineering, Science and Technology, Indus University, Karachi, Sindh, Pakistan
Dr.Engr.Zahid Ali, Faculty of Engineering, Science and Technology, Indus University, Karachi, Sindh, Pakistan
Suresh Kumar, Faculty of Engineering, Science and Technology, Indus University, Karachi, Sindh, Pakistan
Syed Zain ul Abedin Abid, Faculty of Engineering, Science and Technology, Indus University, Karachi, Sindh, Pakistan
Chaman Lal, Faculty of Engineering, Science and Technology, Indus University, Karachi, Sindh, Pakistan

Abstract
Speaker identification is the key area of digital signal processing where the synthesis and noise reduction of speech are the core research areas. Speaker identification system is influenced by the background noise which directly affects the efficiency of system and is still reflected as a challenging question in speaker identification system. Several useful techniques for feature extraction have been proposed and refined. In this paper, the performance of GMM and VQ has been investigated on the basis of their effects in text dependent speaker identification and proposed the optimum techniques for MFCC based speaker identification system.

Keywords
vector –quantization, speaker identification, Gaussian mixture

Cite this paper
Chandar Kumar, Dr.Engr.Zahid Ali, Suresh Kumar, Syed Zain ul Abedin Abid, Chaman Lal, MFCC based performance analysis of VQ and GMM Speaker identification system , SCIREA Journal of Electrical Engineering. Volume 5, Issue 4, August 2020 | PP. 89-99.

References

[ 1 ] Herbert Gish and Michael schimdt, ”Text Independent Speaker Identification” IEEE signal processing magazine, October 1994.
[ 2 ] Faundez-Zanuy M. and Monte-Moreno E. 2005 State-ofthe-art in speaker recognition , Aerospace and Electronic Systems Magazine, IEEE, 20(5), pp. 7-12
[ 3 ] K. Saeed and M. K. Nammous. 2005 Heuristic method of Arabic speech recognition, in Proc. IEEE 7th Int. Conf. DSPA, Moscow, Russia, pp. 528–530.
[ 4 ] Kumar, Chandar, Faizan ur Rehman, Shubash Kumar, Atif Mehmood, and Ghulam Shabir. "Analysis of MFCC and BFCC in a speaker identification system." In Computing, Mathematics and Engineering Technologies (iCoMET), 2018 International Conference on, pp. 1-5. IEEE, 2018.
[ 5 ] D. Olguin, P.A.Goor, and A. Pentland. 2009 Capturing individual and group behavior with wearable sensors, in Proceedings of AAAI Spring Symposium on Human Behavior Modeling
[ 6 ] S. B. Davis and P. Mermelstein. 1980 Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences, IEEE Trans. On ASSP, 28(4), pp. 357-365.
[ 7 ] R. Vergin, B, O Shaughnessy and A. Farhat. 1999 Generalized Mel frequency Cepstral coefficients for large-vocabulary speaker independent continuous-speech recognition, IEEE Trans. On ASSP,7(5), pp. 525-532.
[ 8 ] ur Rehman, Faizan, Chandar Kumar, Shubash Kumar, Atif Mehmood, and Umair Zafar. "VQ based comparative analysis of MFCC and BFCC speaker recognition system." In Information and Communication Technologies (ICICT), 2017 International Conference on, pp. 28-32. IEEE, 2017.
[ 9 ] S.Singh and Dr. E.G Rajan. 2007 A Vector Quantization approach Using MFCC for Speaker Recognition, International conference Systemic, Cybernatics and Informatics ICSCI under the Aegis of Pentagram Research Centre Hyderabad, pp. 786-790.
[ 10 ] K. Sri Rama Murty and B. Yegnanarayana. 2006 Combining evidence from residual phase and MFCC features for speaker recognition, IEEE Signal Processing Letters, 13(1), pp. 52-55.
[ 11 ] Prof. Ch.Srinivasa Kumar, Dr. P. Mallikarjuna Rao “Design Of An Automatic Speaker Recognition System Using MFCC, Vector Quantization And LBG Algorithm” international journal of computer science and Engineering (IJSCE); Aug 2011.
[ 12 ] Vibha Tiwari “MFCC and its applications in speaker recognition” International Journal on Emerging Technologies, 2010.
[ 13 ] Roma Bharti, Priyanka Bansal, “Real Time Speaker Recognition System using MFCC and Vector Quantization Technique”, International Journal of Computer Applications (0975 – 8887) Volume 117 – No. 1, May 2015.
[ 14 ] L. Rabiner and B. H. Jaung ,“Fundamentals of Speech recognition”, Prentice Hall Englewood Cliffs, New Jersey, 1993.
[ 15 ] Chakroborty, S., Roy, A. and Saha, G. 2007 Improved Closed set Text- Independent Speaker Identification by Combining MFCC with Evidence from Flipped Filter Banks , International Journal of Signal Processing, 4(2), pp. 114-122
[ 16 ] Reynolds, D.A.‘ Speaker identification and verification using Gaussian mixture speaker models’, Speech Communication, vol. 17, pp. 91-108,1995.