Parkinson’s disease (PD) is a neurological disorder, progressive in nature. In order to provide customized patient care, diagnosis and monitoring using smart gadgets, smartphones, and smartwatches, there is a need for a system that works in natural as well as controlled environments.
OBJECTIVE AND METHODS:
The primary purpose is to record speech signal, and identify whether the speech signal is Parkinson or not. For this work, a comparison of three feature extraction methods, i.e. Wavelet Packets, MFCC, and a fusion of MFCC and WPT, were carried out. Apart from the feature extraction, two classifiers were used, i.e. HMM and SVM.
RESULTS:
In this study, a fusion of MFCC, WPT with HMM shows the best performance parameters.
CONCLUSION:
The best of the three feature extraction and classifier results are described in this paper.
BockletTNöthEStemmerGRuzickovaHRuszJ. Detection of persons with Parkinson’s disease by acoustic, vocal, and prosodic analysis, in 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings, 2011.
2.
TsanasALittleMAMcSharryPESpielmanJRamigLO. Novel speech signal processing algorithms for high-accuracy classification of Parkinsons disease. IEEE Trans. Biomed. Eng.2012; 59(5): 1264-1271.
3.
HarelBCannizzaroMSnyderPJ. Variability in fundamental frequency during speech in prodromal and incipient Parkinson’s disease: A longitudinal case study. Brain Cogn.2004; 56(1): 24-29.
4.
MaetzlerWKluckenJHorneM. A clinical view on the development of technology-based tools in managing Parkinson’s disease. Mov. Disord.2016; 31(9): 1263-1271.
5.
FaroukMH. Clinical Diagnosis and Assessment of Speech Pathology, in Application of Wavelets in Speech Processing, 2018, pp. 77-80.
6.
BirkholzPMartinLXuYScherbaumSNeuschaefer-RubeC. Manipulation of the prosodic features of vocal tract length, nasality and articulatory precision using articulatory synthesis, Comput Speech Lang, 2017.
7.
MeierMBorskyMMagnusdottirEHJohannsdottirKRGudnasonJ. Vocal tract and voice source features for monitoring cognitive workload, in 7th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2016 – Proceedings, 2017.
8.
KoolagudiSGRaoKS. Emotion recognition from speech: A review, Int. J. Speech Technol.2012; 15(2): 99-117.
9.
BenbaAJilbabAHammouchA. Discriminating between patients with Parkinson’s and neurological diseases using cepstral analysis, IEEE Trans. Neural Syst. Rehabil. Eng., 2016.
10.
ChandrayanSAgarwalAArifMSahuSS. Selection of dominant voice features for accurate detection of Parkinson’s disease, Proc. 3rd Int. Conf. Biosignals, Images Instrumentation, ICBSII 2017, no. March, 2017, pp. 16-18.
11.
CumminsNSchererSKrajewskiJSchniederSEppsJQuatieriTF. A review of depression and suicide risk assessment using speech analysis. Speech Commun.2015; 71: 10-49.
12.
JankovicJ. Parkinson’s disease: clinical features and diagnosis,J. Neurol. Neurosurg. Psychiatry, 2008; 79(4): 368-376.
13.
GoetzCG et al., Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDS-UPDRS): Scale presentation and clinimetric testing results. Mov. Disord.2008; 23(15): 2129-2170.
14.
BazazehDShubairRMalikWQ. Biomarker discovery and validation for Parkinson’s disease: A machine learning approach. Proc IEEE Int. Conf. Bio-engineering Smart Technol, 2016.
15.
WangJHoekstraJGZuoCCookTJZhangJ. Biomarkers of Parkinson’s disease: Current status and future perspectives. Drug Discov. Today, 2013.
16.
SinghGSamavedhamL. Unsupervised learning based feature extraction for differential diagnosis of neurodegenerative diseases: A case study on early-stage diagnosis of Parkinson disease, J. Neurosci. Methods. 2015; 256: 30-40.
17.
DaubechiesI. The continuous wavelet transform, Ten Lect Wavelets.1992; 15(C): 17-52.
18.
FaroukMH. Spectral analysis of speech signal and pitch estimation, in Application of Wavelets in Speech Processing, Springer, 2018, pp. 23-28.
19.
FaroukMH. Speech quality assessment, in Application of Wavelets in Speech Processing, Springer, 2018, pp. 501-506.
20.
RufinerHLNacionalUNosDEGoddardJCElcktricaDI. A method of wavelet selection in phone recognition, Computer Standards & Interfaces. 1997; 20(6-7): 889-891.
21.
FaroukMH, Speech recognition, in Application of Wavelets in Speech Processing, 2018, pp. 41-46.
22.
ZhaoHZhaoLZhaoKWangG. Voice activity detection based on distance entropy in noisy envirnment, 2009 Fifth Int. Jt. Conf. INC, IMS IDC, 2009; 1: 1364-1367.
23.
CaoYGuanYLaDGaoJ. Voice activity detection algorithm based on entropy in noisy environment, in 2016 Chinese Control and Decision Conference (CCDC), 2016, pp. 3799-3803.
24.
Al-AliAKHDeanDSenadjiBBaktashmotlaghMChandranV. Speaker Verification with Multi-Run ICA Based Speech Enhancement, 2017.
25.
Al-AliAKHDeanDSenadjiBChandranVNaikGR, Enhanced Forensic Speaker Verification Using a Combination of DWT and MFCC Feature Warping in the Presence of Noise and Reverberation Conditions, IEEE Access.2017; 5: 15400-15413.
26.
SakarBE et al., Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings, IEEE J. Biomed. Heal. Informatics.2013; 17(4): 828-834.
