Analysis of voiced speech by means of bispectrum

Boyanov, B.; Hadjitodorov, Stefan; Ivanov, Todor

doi:10.1049/el:19911402

Cited by 11 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Majority of real signals do not exhibit normal distribution (e.g., the signals generated by systems with nonlinear dynamics, including speech signal), while the measurement noise can be to a high degree of accuracy described as a colored process with a normal distribution. An additional feature distinguishing the cumulants and poly-spectra is the fact that they contain information concerning amplitude and phase of a given process (e.g., harmonic fluctuations, quadratic phase coupling [5]), while the correlation function and power spectrum contain only the information concerning signal amplitude [6]. The quadratic phase coupling is present in healthy voice in larger extend as opposed to deformed (pathological) speech.…”

Section: Higher-order Statistical Methodsmentioning

confidence: 99%

Analysis of Polish Pathological Speech by Higher Order Spectrum

Wszołek

Kłaczyński

2010

Acta Phys. Pol. A

View full text Add to dashboard Cite

show abstract

Section: Higher-order Statistical Methodsmentioning

confidence: 99%

Analysis of Polish Pathological Speech by Higher Order Spectrum

Wszołek

Kłaczyński

2010

Acta Phys. Pol. A

View full text Add to dashboard Cite

show abstract

“…As a result, recent works consider this new approach in order to reveal discriminative measures between healthy and pathological voices. Examples are measures based on high order statistics (HOS) [18], [19] and AM-FM modelling of voice signal [20]- [23].…”

Section: Introductionmentioning

confidence: 99%

Characterization of Healthy and Pathological Voice Through Measures Based on Nonlinear Dynamics

Henríquez

Alonso

Ferrer

et al. 2009

IEEE Trans. Audio Speech Lang. Process.

131

View full text Add to dashboard Cite

Abstract-In this paper, we propose to quantify the quality of the recorded voice through objective nonlinear measures. Quantification of speech signal quality has been traditionally carried out with linear techniques since the classical model of voice production is a linear approximation. Nevertheless, nonlinear behaviors in the voice production process have been shown. This paper studies the usefulness of six nonlinear chaotic measures based on nonlinear dynamics theory in the discrimination between two levels of voice quality: healthy and pathological. The studied measures are first-and second-order Rényi entropies, the correlation entropy and the correlation dimension. These measures were obtained from the speech signal in the phase-space domain. The values of the first minimum of mutual information function and Shannon entropy were also studied. Two databases were used to assess the usefulness of the measures: a multiquality database composed of four levels of voice quality (healthy voice and three levels of pathological voice); and a commercial database (MEEI Voice Disorders) composed of two levels of voice quality (healthy and pathological voices). A classifier based on standard neural networks was implemented in order to evaluate the measures proposed. Global success rates of 82.47% (multiquality database) and 99.69% (commercial database) were obtained.

show abstract