Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition

@article{Sahidullah2012DesignAA,
  title={Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition},
  author={Md. Sahidullah and Goutam Saha},
  journal={Speech Communication},
  year={2012},
  volume={54},
  pages={543-565}
}
Standard Mel frequency cepstrum coefficient (MFCC) computation technique utilizes discrete cosine transform (DCT) for decorrelating log energies of filter bank output. The use of DCT is reasonable here as the covariance matrix of Mel filter bank log energy (MFLE) can be compared with that of highly correlated Markov-I process. This full-band based MFCC computation technique where each of the filter bank output has contribution to all coefficients, has two main disadvantages. First, the… CONTINUE READING
Highly Cited
This paper has 162 citations. REVIEW CITATIONS
97 Citations
44 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 97 extracted citations

163 Citations

02040'13'15'17
Citations per Year
Semantic Scholar estimates that this publication has 163 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 44 references

An overview of textindependent speaker recognition : From features to supervectors

  • O. Kwon, T. Lee
  • Speech Comm .
  • 2010

Similar Papers

Loading similar papers…