Multitaper MFCC and PLP features for speaker verification using i-vectors

@article{Alam2013MultitaperMA,
  title={Multitaper MFCC and PLP features for speaker verification using i-vectors},
  author={Md. Jahangir Alam and Tomi Kinnunen and Patrick Kenny and Pierre Ouellet and Douglas D. O'Shaughnessy},
  journal={Speech Communication},
  year={2013},
  volume={55},
  pages={237-251}
}
In this paper we study the performance of the low-variance multi-taper Mel-frequency cepstral coefficient (MFCC) and perceptual linear prediction (PLP) features in a state-of-the-art i-vector speaker verification system. The MFCC and PLP features are usually computed from a Hamming-windowed periodogram spectrum estimate. Such a single-tapered spectrum estimate has large variance, which can be reduced by averaging spectral estimates obtained using a set of different tapers, leading to a so… CONTINUE READING
BETA

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • Compared to the MFCC and PLP baseline systems, the sine-weighted cepstrum estimator (SWCE) based multitaper method provides average relative reductions of 12.3% and 7.5% in equal error rate, respectively.
  • Finally, the Thomson multi-taper method provides error reductions of 9.5% and 5.0% in EER for MFCC and PLP features, respectively.

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 41 CITATIONS

Text-independent speaker verification with ant colony optimization feature selection and support vector machine

  • 2015 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA)
  • 2015
VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Improved multitaper PNCC feature for robust speaker verification

  • The 9th International Symposium on Chinese Spoken Language Processing
  • 2014
VIEW 3 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multiple windowed spectral features for emotion recognition

  • 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Feature Selection Applied to G.729 Synthesized Speech for Automatic Speaker Recognition

  • 2018 IEEE 5th International Congress on Information Science and Technology (CiSt)
  • 2018
VIEW 1 EXCERPT
CITES BACKGROUND

Robust speaker verification system in acoustic noise mobile by using Multitaper Gammaton Hilbert Envelope Coefficients

  • 2018 2nd International Conference on Natural Language and Speech Processing (ICNLSP)
  • 2018
VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 34 REFERENCES

A multiple window method for estimation of peaked spectra

  • IEEE Trans. Signal Processing
  • 1997
VIEW 16 EXCERPTS
HIGHLY INFLUENTIAL

Bayesian Speaker Verification with Heavy-Tailed Priors

  • Odyssey
  • 2010
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Optimal cepstrum estimation using multiple windows

  • 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2009
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Multitaper spectral estimation of power law processes

  • IEEE Trans. Signal Processing
  • 1998
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Spectrum estimation and harmonic analysis

  • Proceedings of the IEEE
  • 1982
VIEW 16 EXCERPTS
HIGHLY INFLUENTIAL