Meny

Javascript verkar inte påslaget? - Vissa delar av Lunds universitets webbplats fungerar inte optimalt utan javascript, kontrollera din webbläsares inställningar.
Du är här

Multitaper Estimation of Frequency-Warped Cepstra with Application to Speaker Verification

Författare:
  • Johan Sandberg
  • Maria Sandsten
  • Tomi Kinnunen
  • Rahim Saeidi
  • Patrick Flandrin
  • Pierre Borgnat
Publiceringsår: 2010
Språk: Engelska
Sidor: 343-346
Publikation/Tidskrift/Serie: IEEE Signal Processing Letters
Volym: 17
Nummer: 4
Dokumenttyp: Artikel
Förlag: IEEE

Sammanfattning

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.

Disputation

Nyckelord

  • Technology and Engineering
  • Speech analysis
  • Multitapers
  • Speaker verification
  • Cepstral analysis
  • Multiple windows
  • MFCC

Övriga

  • VR
  • Kungliga fysiografiska sällskapet
Published
Yes

Box 117, 221 00 LUND
Telefon 046-222 00 00 (växel)
Telefax 046-222 47 20
lu [at] lu [dot] se

Fakturaadress: Box 188, 221 00 LUND
Organisationsnummer: 202100-3211
Om webbplatsen