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

Low-Variance Multitaper MFCC Features: A Case Study in Robust Speaker Verification

  • Tomi Kinnunen
  • Rahim Saeidi
  • Filip Sedlak
  • Kong Aik Lee
  • Johan Sandberg
  • Maria Sandsten
  • Haizhou Li
Publiceringsår: 2012
Språk: Engelska
Sidor: 1990-2001
Publikation/Tidskrift/Serie: IEEE Transactions on Audio, Speech, and Language Processing
Volym: 20
Nummer: 7
Dokumenttyp: Artikel i tidskrift
Förlag: IEEE--Institute of Electrical and Electronics Engineers Inc.


In speech and audio applications, short-term signal spectrum is often represented using mel-frequency cepstral coefficients (MFCCs) computed from a windowed discrete Fourier transform (DFT). Windowing reduces spectral leakage but variance of the spectrum estimate remains high. An elegant extension to windowed DFT is the so-called multitaper method which uses multiple time-domain windows (tapers) with frequency-domain averaging. Multitapers have received little attention in speech processing even though they produce low-variance features. In this paper, we propose the multitaper method for MFCC extraction with a practical focus. We provide, first, detailed statistical analysis of MFCC bias and variance using autoregressive process simulations on the TIMIT corpus. For speaker verification experiments on the NIST 2002 and 2008 SRE corpora, we consider three Gaussian mixture model based classifiers with universal background model (GMM-UBM), support vector machine (GMM-SVM) and joint factor analysis (GMM-JFA). Multitapers improve MinDCF over the baseline windowed DFT by relative 20.4% (GMM-SVM) and 13.7% (GMM-JFA) on the interview-interview condition in NIST 2008. The GMM-JFA system further reduces MinDCF by 18.7% on the telephone data. With these improvements and generally noncritical parameter selection, multitaper MFCCs are a viable candidate for replacing the conventional MFCCs.


  • Probability Theory and Statistics
  • Mel-frequency cepstral coefficient (MFCC)
  • multitaper
  • small-variance
  • estimation
  • speaker verification


  • Statistical Signal Processing Group
  • ISSN: 1558-7924

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