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

  title={Low-Variance Multitaper MFCC Features: A Case Study in Robust Speaker Verification},
  author={T. Kinnunen and R. Saeidi and Filip Sedlak and Kong-Aik Lee and J. Sandberg and M. Hansson and Haizhou Li},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  • T. Kinnunen, R. Saeidi, +4 authors Haizhou Li
  • Published 2012
  • Computer Science
  • IEEE Transactions on Audio, Speech, and Language Processing
  • 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. [...] Key Method We provide, first, detailed statistical analysis of MFCC bias and variance using autoregressive process simulations on the TIMIT corpus.Expand Abstract
    Local spectral variability features for speaker verification
    • 32
    • PDF
    A Novel Windowing Technique for Efficient Computation of MFCC for Speaker Recognition
    • 50
    • PDF
    Multiple windowed spectral features for emotion recognition
    • 24
    • PDF
    Adaptive wavelet shrinkage for noise robust speaker recognition
    • 27
    • PDF
    Robust feature extractors for continuous speech recognition
    • 8
    • PDF


    Publications referenced by this paper.
    Speaker Verification Using Adapted Gaussian Mixture Models
    • 4,364
    • PDF
    Feature warping for robust speaker verification
    • 751
    • PDF
    Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se
    • 3,460
    • PDF
    MVA Processing of Speech Features
    • 228
    • PDF
    RASTA processing of speech
    • 1,994
    • PDF