The week's pick
Reseach Article
Analysis of MFCC and Multitaper MFCC Feature Extraction Methods
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 131 - Number 4 |
| Year of Publication: 2015 |
| Authors: Rupali G. Shintri, S.K. Bhatia |
10.5120/ijca2015906883
|
Rupali G. Shintri, S.K. Bhatia . Analysis of MFCC and Multitaper MFCC Feature Extraction Methods. International Journal of Computer Applications. 131, 4 ( December 2015), 7-10. DOI=10.5120/ijca2015906883
Abstract
In speech & audio applications, short-term signal spectrum is often represented using mel-freuency cepstral coefficient (MFCC) computed from a windowed discrete Fourier transform (DFT). Windowing reduces spectral leakage but variance of the spectrum estimate remains high. An extension to windowed DFT is called multitaper method which uses multiple time domain windows which are called as tapers with frequency domain averaging. Then detailed statistical analysis of MFCC bias & variance is done. For speaker verification the extracted feature is used to design a model using classifier (GMM), which implements likelihood ratio test to decide whether to accept or deny the registered speaker.
References
- Kinnunen T., Li.,H. An overview of Text Independent Speaker recognition:from feature to supervectors Speechcommunication(2009),doi:10.1016/j.specom.2009.08.009
- Tomi kinnuen,Rahim saeidi, Low-Variance Multitaper MFCC features: a case study in robust speakerVerification member IEEE, Manuscript IEEE ransaction in Speech & Audio processing(2012).
- Patrick Kenny1, Douglas O’Shaughnessy2, Study of Low-variance Multi-taper Features for Distributed Speech Recognition, INRS-EMT, University of Quebec, Montreal, Canada Speech Confrernce (2008)
- G.Suvarna Kumar ,K. A. Raju, Dr.MahanRao, P.Satheesh, Speaker Recognition Using GMM, et.al/International Journal Of Engineering Science &Technology Vol2 (6), 2428-2436, 2010.
- H. Hermansky and N. Morgan. RASTA processing of speech. IEEE Trans. on Speech and Audio Processing, 2(4):578–589, October 1994.
- Puming zhan,Martin westphal, Speaker Normalization Based On Frequency Warping, Article in Interactive system laboratories,Carnegie University Germany,
- David McCarten E6820, Comparison of Speech Normalization Techniques, Student, Columbia University March 9, 2008
- Douglas.A.Reynolds, Automatic Speaker Recognition :Current Approaches & Feature Trends by, MIT Lincoln Laboratories, Lexington, MA,USA.
- Yongxin Zhang, Adel Iskander Fahmy, Michael S. Scordilis “Speaker Verification Using Speaker-Specific Prompts” department of electrical and computer engineering, university of miami, coral gables, florida 33124
- Mohd Zaizu Ilyas, Member, IEEE, Salina Abdul Samad, Senior Member, IEEE, Aini Hussain, Member , IEEE and Khairul Anuar Ishak, Member, IEEE, “Speaker Verification using Vector Quantization and Hidden Markov Model”, the 5th student conference on research and development –scored 2007 11-12 december 2007, malaysia
- Gibak Kim and Philipos C. Loizou, Senior Member, IEEE, “Improving Speech Intelligibility in Noise Using Environment-Optimized Algorithms”, IEEE transaction on audio ,speech & language processing ,vol.18.no.8,november 2010.
- Alfredo Maesa1, Fabio Garzia1,2, Michele Scarpiniti1, Roberto Cusani1,” Text Independent Automatic Speaker Recognition System Using Mel-Frequency Cepstrum Coefficient and Gaussian Mixture Models” journal of information security,2012,3335-340.
Index Terms
Keywords