Date of Publication :15th September 2017
Abstract: A text dependent speaker recognition system can be developed by using MFCC and Vector Quantization in a controlled environment. But MFCC with Vector Quantization cannot be useful for developing a text independent speaker recognition system and also does not provide accurate results. So, the main aim of this paper is to develop a text independent speaker recognition system using MFCC and GMM along with NLMS adaptive filter, such that the input utterance is given in real time using a microphone. NLMS adaptive filter is used to reduce the noise in the speech signal and then passed through the feature extraction phase. It is developed as Text- independent Speaker Recognition System with 50 speakers and also uses the locally recorded database for training. The performance of the proposed system tested in real time using Adaptive filter based on the log likelihood scores.
Reference :
-
[1] M.S.Sinith, AnoopSalim, GowriSankar K, Sandeep Narayanan K V, Vishnu Soman “A Novel Method for Text-Independent Speaker Identification Using MFCC and GMM” ICALIP2010 ©2010 IEEE.
[2] Roshny Jose George “Design Of an Adaptive Filtering Algorithm for Noise Cancellation “International Research Journal of Engineering and Technology (IRJET), Volume: 02 Issue: 04 | July2015.
[3] John Creighton and R.Doraiswami“Real Time Implementation Of anAdaptive Filter For Speech Enhancement” 2004 IEEE.
[4] Wenyong Lin “An improved GMM based clustering algorithm for efficient speaker identification” 2015 4th International Conference on Computer Science and Network Technology (ICCSNT 2015) ©2015 IEEE.
[5] Michael Lutter “Mel Frequency Cepstral Coefficients (feature extraction/ Mfcc)” The Speech Recognition Wiki25 November 2014.
[6] J.P.Campbell, “Speaker Recognition: A Tutorial”, Proc. Of the IEEE, Vol 85,No. 9, September 1997,pp. 1437-1462.
[7] VibhaTiwari “MFCC and its applications in speaker recognition ”International Journal on Emerging Technologies 1(1): 19-22(2010) ISSN : 0975-8364.
[8] Rania Chakroun, Leila BeltaïfaZouari, MondherFrikha, and Ahmed Ben Hamida “ Improving Text-independent speaker recognition with GMM” 2nd International Conference on Advanced Technologies for Signal and Image Processing - ATSIP'2016 March 21-24, 2016, Monastir, Tunisia ©2016 IEEE.
[9] Prof.Vaishali M. Karne, Prof.Akhilesh Singh Thakur , Dr.VibhaTiwari “ Least Mean Square (LMS) Adaptive Filter For Noise Cancellation “International Journal of Application or Innovation in Engineering & Management (IJAIEM) , ISSN 2319 – 4847.
[10]SourjyaSarkar, K.SreenivasaRao “Speaker Verification in Noisy Environment Using GMM Super vectors” © 2013 IEEE.
[11]Sheng Zhang, student Member, IEEE, Jiashu Zhang, and HongyuHan ”Robust Variable Step-Size Decorrelation Normalized Least-Mean Square Algorithm and its Application to Acoustic Echo Cancellation” IEEE/ACM Transactions on Audio Speech, and Language Processing.
[12]Xin-xing ling, Ling Zhan, Hong Zhao, Ping Zhou “Speaker Recognition System Using the Improved GMM-based Clustering Algorithm” ©2010 IEEE.
[13]Yuan Liu, Tianfan Fu, Yuchen Fan, YanminQian, Kai Yu “Speaker Verification with Deep Features“2014 International Joint Conference on Neural Networks (IJCNN) , July 6-11, 2014, Beijing, China, ©2014 IEEE.
[14]SourjyaSarkar, K. SreenivasaRao “Significance Of Utterance Partitioning In GMM-SVM Based Speaker Verification In Varying Background Environment
[15]RandheerBagi, JainathYadav, K. SreenivasaRao “Improved Recognition Rate of Language Identification System in Noisy Environment” ©2015 IEEE.
[16]JYOTI DHIMAN, SHADAB AHMAD, KULDEEP GULIA “ Comparison between Adaptive filter Algorithms (LMS, NLMS and RLS)”International Journal of Science, Engineering and Technology Research (IJSETR) Volume 2, Issue 5, May 2013, ISSN: 2278 – 7798.
[17]Douglas A. Reynolds “Speaker Identification and verification using Gaussian Mixture speaker models” speech communication 17 (1995), ELSEVIER