Review Papers | Electronics & Communication Engineering | India | Volume 4 Issue 9, September 2015
Review: MFCC & Multitaper MFCC Feature Extraction for Speaker Verification
Rupali G Shintri | S. K. Bhatia 
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 build a model using classifier (GMM), which implements likelihood ratio test to decide whether to accept or reject the speaker.
Keywords: Mel-frequency cepstral coefficient, multitaper, GMM, speaker verification, tapers
Edition: Volume 4 Issue 9, September 2015,
Pages: 1863 - 1865
How to Cite this Article?
Rupali G Shintri, S. K. Bhatia, "Review: MFCC & Multitaper MFCC Feature Extraction for Speaker Verification", International Journal of Science and Research (IJSR), Volume 4 Issue 9, September 2015, pp. 1863-1865, https://www.ijsr.net/get_abstract.php?paper_id=SUB158533
How to Share this Article?
Similar Articles with Keyword 'GMM'
Overview of Analyzing Real Time Segmentation of High Definition Video using Gaussian Mixture Model Algorithm on FPGA
Manu K S | Dr. Rekha K.R | Dr. Nataraj K. R.
Survey on 'Singing Voice Separation and Singing Voice Classifier Technique for Voice Separation from Music Accompaniments'
Nichal Vikas R. | Mane Vikram A