The Delta-Phase Spectrum With Application to Voice Activity Detection and Speaker Recognition
- 31 January 2011
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 19 (7) , 2026-2038
Abstract
For several reasons, the Fourier phase domain is less favored than the magnitude domain in signal processing and modeling of speech. To correctly analyze the phase, several factors must be considered and compensated, including the effect of the step size, windowing function and other processing parameters. Building on a review of these factors, this paper investigates a spectral representation based on the Instantaneous Frequency Deviation, but in which the step size between processing frames is used in calculating phase changes, rather than the traditional single sample interval. Reflecting these longer intervals, the term delta-phase spectrum is used to distinguish this from instantaneous derivatives. Experiments show that mel-frequency cepstral coefficients features derived from the delta-phase spectrum (termed Mel-Frequency delta-phase features) can produce broadly similar performance to equivalent magnitude domain features for both voice activity detection and speaker recognition tasks. Further, it is shown that the fusion of the magnitude and phase representations yields performance benefits over either in isolation.Keywords
This publication has 37 references indexed in Scilit:
- Short-time phase spectrum in speech processing: A review and some experimental resultsDigital Signal Processing, 2007
- Using the matrix pencil method to solve phase unwrappingIEEE Transactions on Signal Processing, 2003
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000
- Score Normalization for Text-Independent Speaker Verification SystemsDigital Signal Processing, 2000
- Improving the readability of time-frequency and time-scale representations by the reassignment methodIEEE Transactions on Signal Processing, 1995
- RASTA processing of speechIEEE Transactions on Speech and Audio Processing, 1994
- A fast and accurate single frequency estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Derivative of phase spectrum of truncated autoregressive signalsIEEE Transactions on Circuits and Systems, 1985
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- A new phase unwrapping algorithmIEEE Transactions on Acoustics, Speech, and Signal Processing, 1977