Voiced/Unvoiced Detection of Speech Signals Using Empirical Mode Decomposition Model

Hirose

Hasan

2015

Pattern Anal Applic

Self Cite

This paper introduces a robust voiced/nonvoiced (VnV) speech classification method using bivariate empirical mode decomposition (bEMD). Fractional Gaussian noise (fGn) is employed as the reference signal to derive a data adaptive threshold for VnV discrimination. The analyzing speech signal and fGn are combined to generate a complex signal which is decomposed into a finite number of complex-valued intrinsic mode functions (IMFs) by using bEMD. The real and imaginary parts of the IMFs represent the IMFs of observed speech and fGn, respectively. The log-energies of both types of IMFs are calculated. There exist similarities between the IMF logenergy representation of fGn and unvoiced speech signals. Hence, the upper confidence limit from IMF log-energies of fGn is used as data adaptive threshold for VnV classification. If the subband log-energy of speech segment exceeds the threshold, the segment is classified as voiced and unvoiced otherwise. The experimental results show that the proposed algorithm performs better than the recently reported methods without requiring any training data for a wide range of SNRs.

Section: Why Bemd With Fgnmentioning

confidence: 99%

Voiced/non-voiced speech classification using adaptive thresholding with bivariate EMD

Hirose

Hasan

2015

Pattern Anal Applic

Self Cite

“…As the pitch range for both male and female utterances lies between 50-500 Hz (Molla et al 2007), a significant portion of the high frequency components is filtered out in the frequency domain. The resultant signal ϕ(n) is termed as pre-filtered speech (PFS) which contains less noise as the high frequency components are mainly due to noise are suppressed.…”

Section: Pitch Estimation Algorithmmentioning

confidence: 99%

“…Finally, the pitch period of the subband is selected as final pitch which is closer to the preliminary estimated pitch period of the speech frame. Although the performance of the priori pitch based EMD (pEMD) method is better than the NACF (Kasi and Zahorian 2002) and WAC (Shimamura and Kobayashi 2001) (comparison is presented in Molla et al 2007), it is very much sensitive to the priori pitch information which does not tend to any standard pitch estimation method. Pitch estimation is also performed in the time-frequency domain using EMD but these are not noise robust (Huang and Pan 2005;Yang et al 2004).…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Harmonic modification and data adaptive filtering based approach to robust pitch estimation

Roy

Hirose

et al. 2011

Int J Speech Technol

Self Cite

A novel and robust pitch estimation method is presented in this paper. The basic idea is to reshape the speech signal using a combination of the dominant harmonic modification (DHM) and data adaptive time domain filtering techniques. The noisy speech signal is filtered within the ranges of fundamental frequencies to obtain the pre-filtered signal (PFS). The dominant harmonic (DH) of the PFS is determined and enhanced its amplitude. Normalized autocorrelation function (NACF) is applied to that modified signal. Then empirical mode decomposition (EMD) based data adaptive time domain filtering is applied to the NACF signal. Partial reconstruction is performed in EMD domain. The pitch period is determined from the partially reconstructed signal. The experimental results show that the proposed method performs better than the other recently developed methods for noisy and clean speech signals in terms of gross and fine pitch errors.

“…The speech signal is being non-stationary these transformations are not suitable enough. As a data adaptive signal analysis tool EMD is recently used for pitch estimation [19,52,53].…”

Section: Pitch Estimationmentioning

confidence: 99%

Empirical Mode Decomposition for Advanced Speech Signal Processing

Journal of Signal Processing

Das

Hamid

et al. 2013

Self Cite

Empirical mode decomposition (EMD) is a newly developed tool to analyze nonlinear and non-stationary signals.It is used to decompose any signal into a finite number of time varying subband signals termed as intrinsic mode functions (IMFs). Such data adaptive decomposition is recently used in speech enhancement. This study presents the concept of EMD and its application to advanced speech signal processing paradigms including speech enhancement by soft-thresholding, voiced/unvoiced (V/Uv) speech discrimination and pitch estimation. The speech processing is frequently performed in the transformed domain and the transformation is usually achieved by traditional signal analysis techniques i.e. Fourier and wavelet transformations. These analysis methods employ priori basis function and it is not suitable for data adaptive analysis for non-stationary signal like speech. Recently, EMD is taken much attention for speech signal processing in data adaptive way. Several EMD based potential soft-thresholding algorithms for speech enhancement are discussed here. The V/Uv discrimination is an important concern in speech processing. It is usually performed by using acoustic features. The training data is used to determine the threshold for classification. The EMD based data adaptive thresholding approach is developed for V/Uv discrimination without any training phase. Noticeable improvement is achieved with the application of EMD in pitch estimation of noisy speech signals. The related experimental results are also presented to realize the effectiveness of EMD in advanced speech processing algorithms.