The overall aim of this study was to apply local intrinsic dimension (Di) estimation to quantify high-dimensional, disordered voice and discriminate between the 4 types of voice signals. It was predicted that continuous Di analysis throughout the entire time-series would generate comprehensive descriptions of voice signal components, called voice type component profiles (VTCP), that effectively distinguish between the 4 voice types.
Method:
One hundred thirty-five voice recording samples of the sustained vowel /a/ were obtained from the Disordered Voice Database Model 4337 and spectrographically classified into the voice type paradigm. The Di and correlation dimension (D2) were then used to objectively analyze the voice samples and compared based on voice type differentiation efficacy.
Results:
The D2 exhibited limited effectiveness in distinguishing between the 4 voice type signals. For Di analysis, significant differences were primarily observed when comparing voice type component 1 (VTC1) and 4 (VTC4) across the 4 voice type signals (P < .001). The 4 voice type components (VTCs) significantly differentiated between low-dimensional, type 3 and high-dimensional, type 4 signals (P < .001).
Conclusions:
The Di demonstrated improvements over D2 in 2 distinct manners: enhanced resolution at high data dimensions and comprehensive description of voice signal elements.
CohenSMKimJRoyNAscheCCoureyM.The impact of laryngeal disorders on work-related dysfunction. Laryngoscope. 2010;122:1589-1594.
2.
BhutaTPatrickLGarnettJD.Perceptual evaluation of voice quality and its correlation with acoustic measurements. J Voice. 2004;18(3):299-304.
3.
AwanSNRoyNZhangDCohenSM.Validation of the cepstral spectral index of dysphonia (CSID) as a screening tool for voice disorders: development of clinical cutoff scores. J Voice. 2016;30(2):130-144.
4.
KempsterGBGerrattBRAbbottKVBarkmeier-KraemerJHillmanRE.Consensus auditory-perceptual evaluation of voice: development of a standardized clinical protocol. Am J Speech Lang Pathol. 2009;18(2):124-132.
5.
NemrKSimões-ZenariMCordeiroGFet al. GRBAS and Cape-V scales: high reliability and consensus when applied at different times. J Voice. 2012;26(6):812.e17-812.e22.
6.
KreimanJGerrattBR.Validity of rating scale measures of voice quality. J Acoust Soc Am. 1998;104(3pt 1):1598-1608.
7.
MilletBDejonckerePH.What determines the differences in perceptual rating of dysphonia between experienced raters?Folia Phoniatr Logop. 1998;50:305-310.
GuptaRChaspariTKimJKumarNBoneDNarayananS.Pathological speech processing: state-of-the-art, current challenges, and future directions. IEEE Conference Proceedings. 2016;6470-6474.
10.
ZhangYJiangJJ.Acoustic analyses of sustained and running voices from patients with laryngeal pathologies. J Voice. 2008;22(1):1-9.
11.
LienYSMichenerCMEadieTLSteppCE.Individual monitoring of vocal effort with relative fundamental frequency: relationships with aerodynamics and listener perception. J Speech Lang Hear Res. 2015;58(3):566-575.
12.
AwanSNRoyNJiangJJ.Nonlinear dynamic analysis of disordered voice: the relationship between the correlation dimension (D2) and pre-/post-treatment change in perceived dysphonia severity. J Voice. 2010;24(3):285-293.
13.
YuPOuaknineMRevisJGiovanniA.Objective voice analysis for dysphonic patients: a multiparametric protocol including acoustic and aerodynamic measurements. J Voice. 2001;15(4):529-542.
14.
BrockmannMDrinnanMJStorckCCardingPN.Reliable jitter and shimmer measurements in voice clinics: the relevance of vowel, gender, vocal intensity, and fundamental frequency effects in a typical clinical task. J Voice. 2011;25(1):44-53.
15.
VieiraMNMcInnesFRJackMA.On the influence of laryngeal pathologies on acoustic and electroglottographic jitter measures. J Acoust Soc Am. 2002;111(2):1045-1055.
16.
ZhangYJiangJJWallaceSMZhouL.Comparison of nonlinear dynamic methods and perturbation methods for voice analysis. J Acoust Soc Am. 2005;118(4):2551-2560.
17.
SprottJC.Chaos and Time-Series Analysis. Oxford: Oxford University Press; 2006.
18.
ZhangYJiangJJBiazzoLJorgensenM.Perturbation and nonlinear dynamic analyses of voices from patients with unilateral laryngeal paralysis. J Voice. 2005;19(4):519-528.
19.
GiovanniAOuaknineMTrigliaJM.Determination of largest Lyapunov exponents of vocal signal: application to unilateral laryngeal paralysis. J Voice. 1999;13(3):341-354.
20.
JiangJJZhangYMcGilliganC.Chaos in voice, from modeling to measurement. J Voice. 2005;20(1):2-17.
21.
JiangJJZhangYFordCN.Nonlinear dynamics of phonations in excised larynx experiments. J Acoust Soc Am. 2003;114(4pt 1):2198-2205.
22.
MacCallumJKCaiLZhangYJiangJJ.Acoustic analysis of aperiodic voice: perturbation and nonlinear dynamic properties in esophageal phonation. J Voice. 2009;23(3):283-290.
23.
ZhangYMcGilliganCZhouLVigMJiangJJ.Nonlinear dynamic analysis of voices before and after surgical excision of vocal polyps. J Acoust Soc Am. 2004;115(5):2270-2277.
24.
LiLZhangYCalawertsWJiangJJ.Vibratory dynamics of four types of excised larynx phonations. J Voice. 2016;30(6):649-655.
25.
SprecherAOlszewskiAJiangJJZhangY.Updating signal typing in voice: addition of type 4 signals. J Acoust Soc Am. 2010;127(6):3710-3716.
TaoCJiangJJ.Chaotic component obscured by strong periodicity in voice production system. Phys Rev E Stat Nonlin Soft Matter Phys. 2008;77(6 pt 1):061922.
28.
ChoiSHLeeJSprecherAJJiangJJ.The effect of segment selection on acoustic analysis. J Voice. 2012;26(1):1-7.
29.
KumarAMullickSK.Nonlinear dynamical analysis of speech. J Acoust Soc Am. 1996;100(1):615-629.
30.
NeubauerJEdgertonMHerzelH.Nonlinear phenomena in contemporary vocal music. J Voice. 2004;18(1):1-12.
31.
CarterKMRaichRHeroAO.On local intrinsic dimension estimation and its applications. IEEE Trans Signal Process. 2010;58(2):650-663.
32.
CostaJAGirotraAHeroAO.Estimating local intrinsic dimension with k-nearest neighbor graphs. IEEE Workshop on Statistical Signal Processing Proceedings. 2005;417-421.
33.
CostaJAHeroAO.Geodesic entropic graphs for dimension and entropy estimation in manifold learning. IEEE Trans Signal Process. 2004;52(8):2210-2221.
34.
LiXNgMKCongGYeYWuQ.MR-NTD: manifold regularization nonnegative tucker decomposition for tensor data dimension reduction and representation. IEEE Trans Neural Netw Learn Syst. 2017;28(8):1787-1800.
35.
SongSGongYZhangYHuangGHuangGB.Dimension reduction by minimum error minimax probability machine. IEEE Trans Syst Man Cybern Syst. 2017;47(1):58-69.
36.
JiangJJZhangY.Chaotic vibration induced by turbulent noise in a two-mass model of vocal folds. J Acoust Soc Am. 2002;112:2127-2133.
37.
PackardNHCrutchfieldJPFarmerJDShawRS.Geometry from a time series. Phys Rev Lett. 1980;45(9):712-716.
38.
FraserAMSwinneyHL.Independent coordinates for strange attractors from mutual information. Phys Rev A. 1986;33(2):1134-1140.
39.
GrassbergerPProcacciaI.Characterization of strange attractors. Phys Rev Lett. 1983;50(5):346-349.
LinLCalawertsWMDoddKJiangJJ.An objective parameter for quantifying the turbulent noise portion of voice signals. J Voice. 2016;30(6):664-669.
42.
CalawertsWMLinLSprottJCJiangJJ.Using rate of divergence as an objective measure to differentiate between voice signal types based on the amount of disorder in the signal. J Voice. 2017;31(1):16-23.
43.
LiuBPolceEJiangJJ.An objective parameter to classify voice signals based on variation in energy distribution [published May 18, 2018]. J Voice.
