Research Article
Comparative Study on the Performance of Mel-Frequency Cepstral Coefficients and Linear Prediction Cepstral Coefficients under different Speaker’s Conditions
|
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
| Volume 90 - Issue 11 |
| Published: March 2014 |
| Authors: Kamil Ismaila Adeniyi, Oyeyiola Abdulhamid K. |
10.5120/15767-4460
|
Kamil Ismaila Adeniyi, Oyeyiola Abdulhamid K. . Comparative Study on the Performance of Mel-Frequency Cepstral Coefficients and Linear Prediction Cepstral Coefficients under different Speaker’s Conditions. International Journal of Computer Applications. 90, 11 (March 2014), 38-42. DOI=10.5120/15767-4460
@article{ 10.5120/15767-4460,
author = { Kamil Ismaila Adeniyi,Oyeyiola Abdulhamid K. },
title = { Comparative Study on the Performance of Mel-Frequency Cepstral Coefficients and Linear Prediction Cepstral Coefficients under different Speaker’s Conditions },
journal = { International Journal of Computer Applications },
year = { 2014 },
volume = { 90 },
number = { 11 },
pages = { 38-42 },
doi = { 10.5120/15767-4460 },
publisher = { Foundation of Computer Science (FCS), NY, USA }
}
%0 Journal Article
%D 2014
%A Kamil Ismaila Adeniyi
%A Oyeyiola Abdulhamid K.
%T Comparative Study on the Performance of Mel-Frequency Cepstral Coefficients and Linear Prediction Cepstral Coefficients under different Speaker’s Conditions%T
%J International Journal of Computer Applications
%V 90
%N 11
%P 38-42
%R 10.5120/15767-4460
%I Foundation of Computer Science (FCS), NY, USA
Abstract
This paper compares Mel-Frequency Cepstral Coefficients (MFCCs) and Linear Prediction Cepstral Coefficients (LPCCs) features under three speaker conditions: waking up, being fully awake and being tired, to determine which is better at handling the effect of these variations. A Gaussian Mixture Model (GMM) Classifier was used for both features. Experimental results show an identification rate of 83. 3% in the MFCC based system when the speakers were just waking up, while the LPCC based system had a lower identification rate of 75%. Also, when the speakers were either fully awake or tired, the MFCC based system achieved an identification rate of 100%, while the LPCC based system had an Identification rate of 91. 7%. In speaker verification, under the first condition (Waking Up), there is a significant difference between the equal error rates (EER), 7. 9% for MFCC and 22. 0% for LPCC. Also, there is a significant difference between the total success rates (TSR) under this condition. 82. 5% for MFCC and 65. 0% for LPCC. Overall, MFCC achieved a better total success rate under the three conditions studied.
References
- Beigi, H. 2011, Fundamentals of Speaker Recognition, New York: Springer Science and Business Media, Inc.
- Rashid, R. A. , Mahalin, N. H. , Sarijari, M. A. , Abdul Aziz, A. A. , 2008. "Security system using biometric technology: Design and implementation of Voice Recognition System (VRS)," Computer and Communication Engineering, 2008. ICCCE 2008. International Conference on, vol. , no. , pp. 898,902, 13-15.
- Currie, D. , 2003. Shedding some light on Voice Authentication, SANS Institute, GSEC- V1. 4b.
- http://en. wikipedia. org/wiki/Speaker_recognition
- http://www. nou. edu. ng/NOUN_OCL/pdf/SMS/MBF%20841%20EMERGING%20TECHNOLOGIES%20IN%20INFORMATION%20TECHNOLOGY. pdf
- Kinnunen, T. and Li, H. 2009. An Overview of Text-Independent Speaker Recognition: from Features to Supervectors, pp. 1-14.
- Reynolds, D. A. ; Rose, R. C. ; , 1995. "Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models", IEEE Trans. Speech, Audio Processing. vol. 3, no. 1, pp. 72-83.
- Abdallah, S. J. , Osman, I. M. and Mustafa, M. E. 2012. "Text-Independent Speaker Identification Using Hidden Markov Model", World of Computer Science and Information Technology Journal (WCSIT), Vol. 2, No. 6, pp 203-208.
- Ibiyemi T. S. , Aliyu S. A. , Akintola A. G. 2012. "Face and Speech Recognition Fusion in Personal Identification", International Journal of Computer Applications, vol. 47, no. 23, pp 36-41.
- Ouzounov, A. 2010. "Cepstral Features and Text-Dependent Speaker Identification – A Comparative Study", Cybernetics and Information Technologies, Vol. 10, No 1, pp 3-12.
- https://tv. unsw. edu. au/files//unswPDF/Chapter3. pdf
- www. ee. ucla. edu/~ingrid/ee213a/speech/vlad_present. pdf
- Teknomo, Kardi. K-Means Clustering Tutorials. http:\people. revoledu. comkardi tutorialkMean
- Ilyas, M. Z. , Samad, S. A. , Hussain, A. and Ishak, K. A. 2007. "Speaker Verification using Vector Quantization and Hidden Markov Model", Proc. The 5th Student Conference on Research and Development, Malaysia.
Index Terms
Keywords