Speech waveform perturbation analysis revisited
نویسندگان
چکیده
The c l in ica l usefulness of seven acoustic measures of cycle-to-cycle variations (perturbations) in the speech waveform was investigated. Three of these measures referred t o the frequency of occurrence and severeness of waveform perturbations i n special selected parts of the speech identified by means of the r a t e of change of the fundamental frequency. Three other measures referred t o s t a t i s t i c a l properties of the dis t r ibut ion of the re la t ive frequency differences (DFo) between adjacent pitch periods. One perturbation measure referred t o the percentage of consecutive pitch period differences with alternating signs. The acoustic measures were tested on tape recorded speech samples from 41 voice patients, before and a f t e r successful therapy. A l l measures were calculated automatically and applied t o running speech. Scatterograms of the acoustic measures and a sum of perceived deviant voice qual i t ies as rated by voice cl inicians are presented. The different perturbation measures are compared as regards the acousticperceptual correlation and the ability to discriminate between normal and pathological voice status. The standard deviation of the DFodis t r ibut ion is suggested as the most useful acoustic measure of waveform perturbations for clinical applications.
منابع مشابه
Spectral tilt as a perturbation-free measurement of noise levels in voice signals
Acoustic analysis of voice quality proves useful in the objective assessment of voice disorders and for motivating new components for use in improving voice synthesis. A commonly used quantitative spectral index is the harmonicsto-noise ratio (HNR), which gives gross information regarding speech signal periodicity. However, as the measure is sensitive to all forms of waveform aperiodicities (no...
متن کاملCrafting Adversarial Examples For Speech Paralinguistics Applications
Computational paralinguistic analysis is increasingly being used in a wide range of applications, including securitysensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While state-ofthe-art machine learning techniques, such as deep neural networks, can provide robust and accurate speech analysis, they are susceptible to adversarial attacks. ...
متن کاملAnalysis and perception of speech under physical task stress
It is known that speech under physical task stress degrades speech system performance. Therefore, an analysis of speech under physical task stress is performed across several parameters to identify acoustic correlates. Formal listener tests are also performed to determine the relationship between acoustic correlates and perception. To verify the statistical significance of all results, student-...
متن کاملOverview of Code Excited Linear Predictive Coder
Advances in speech coding technologies have enabled speech coders to achieve bit-rate reductions at a great extent while maintaining roughly the same speech quality. One of the most important driving forces behind this feat is the analysis-by-synthesis paradigm. Code Excited Linear Predictive coder (CELP) is the quite efficient closed loop analysis-by-synthesis method for narrow and medium band...
متن کامل