Multitaper Estimation of Frequency-Warped Cepstra with Application to Speaker Verification
Author
Summary, in English
Usually the mel-frequency cepstral coefficients are estimated either from a periodogram or from a windowed periodogram. We state a general estimator which also includes multitaper estimators. We propose approximations of the variance and bias of the estimate of each coefficient. By using Monte Carlo computations, we demonstrate that the approximations are accurate. Using the proposed formulas, the peak matched multitaper estimator is shown to have low mean square error (squared bias + variance) on speech-like processes. It is also shown to perform slightly better in the NIST 2006 speaker verification task as compared to the Hamming window conventionally used in this context.
Department/s
- Mathematical Statistics
- Statistical Signal Processing Group
Publishing year
2010
Language
English
Pages
343-346
Publication/Series
IEEE Signal Processing Letters
Volume
17
Issue
4
Document type
Journal article
Publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
Topic
- Probability Theory and Statistics
Keywords
- Speech analysis
- Multitapers
- Speaker verification
- Cepstral analysis
- Multiple windows
- MFCC
Status
Published
Research group
- Statistical Signal Processing Group
ISBN/ISSN/Other
- ISSN: 1070-9908