This paper presents a novel method for speech recognition by utilizing nonlinear/chaotic signal processing techniques to extract time-domain based phase space features. By exploiting the theoretical results derived in nonlinear dynamics, a processing space called a reconstructed phase space can be generated where a salient model (the natural distribution of the attractor) can be extracted for s...

The current paper proposes skew Gaussian mixture models for speaker recognition and an associated algorithm for its training from experimental data. Speaker identification experiments were conducted, in which speakers were modeled using the familiar Gaussian mixture models (GMM), and the new skewGMM. Each model type was evaluated using two sets of feature vectors, the mel-frequency cepstral coe...

In this paper, we consider the use of multiple acoustic features of the speech signal for continuous speech recognition. A novel articulatory motivated acoustic feature is introduced, namely the spectrum derivative feature. The new feature is tested in combination with the standard Mel Frequency Cepstral Coefficients (MFCC) and the voicedness features. Linear Discriminant Analysis is applied to...

In this paper, an efficient speech recognition system is proposed for speaker-independent isolated digits (0 to 9). Using the Weighted MFCC (WMFCC), low computational overhead is achieved since only 13 weighted MFCC coefficients are used. In order to capture the trends of the extracted features, the local and global features are computed using the Improved Features for Dynamic Time Warping (IFD...

In this paper we study the performance of the low-variance multi-taper Mel-frequency cepstral coefficient (MFCC) and perceptual linear prediction (PLP) features in a state-ofthe-art i-vector speaker verification system. The MFCC and PLP features are usually computed from a Hamming-windowed periodogram spectrum estimate. Such a singletapered spectrum estimate has large variance, which can be red...

Current countermeasures used in spoof detectors (for speech synthesis (SS) and voice conversion (VC)) are generally phase-based (as vocoders in SS and VC systems lack phaseinformation). These approaches may possibly fail for nonvocoder or unit-selection-based spoofs. In this work, we explore excitation source-based features, i.e., fundamental frequency (F0) contour and strength of excitation (S...

In this paper, we present two robust feature extractors that use a regularized minimum variance distortionless response (RMVDR) spectrum estimator instead of the discrete Fourier transform-based direct spectrum estimator, used in many front-ends including the conventional MFCC, for estimating the speech power spectrum. Direct spectrum estimators, e.g., single tapered periodogram, have high vari...

We present a computational study of a recently developed molecular fractionation with conjugated caps (MFCC) method for application to peptide/protein that has disulfide bonds. Specifically, we employ the MFCC approach to generate peptide fragments in which a disulfide bond is cut and a pair of conjugated caps are inserted. The method is tested on two peptides interacting with a water molecule....

While most schemes for automatic cover song identification have focused on note-based features such as HPCP and chord profiles, a few recent papers surprisingly showed that local self-similarities of MFCC-based features also have classification power for this task. Since MFCC and HPCP capture complementary information, we design an unsupervised algorithm that combines normalized, beatsynchronou...

The detection of human and spoofed (synthetic/converted) speech has started to receive more attention. In this study, relative phase information extracted from a Fourier spectrum is used to detect human and spoofed speech. Because original/natural phase information is almost entirely lost in spoofed speech using current synthesis/conversion techniques, a modified group delay based feature, the ...