Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods

Mario Lopez-Rodríguez, Mireya Sarai García-Vázquez, Luis Miguel Zamudio-Fuentes, Alejandro Ramírez-Acosta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Dysphonia is a vocal impediment that appears as a symptom of Parkinson’s disease, and can be used for its diagnosis. Among the important measurements for dysphonia detection are jitter, shimmer, fundamental frequency (F0), Harmonics to noise ratio (HNR) and noise to harmonics ratio (NHR). The frequency space of the speech signal is used to detect these five dysphonia measurements, through this space the acoustic markers jitter, shimmer and F0 are calculated. In this article, an evaluation of the detection of acoustic markers is presented through the mathematical methods of the Constant Q Transform (CQT) and the Mel Frequencies Cepstral Coefficients (MFCC) in speech signals of patients with Parkinson’s disease. The classifier method Support Vector Machine (SVM) is used to detect the Biomarkers. According to the results, the CQT method and MFCC method (57% and 62% precision respectively) which is a promising results for Parkinson’s disease diagnosis by the detection of Dysphonia measurements.

Original languageEnglish
Title of host publicationFuture Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019
EditorsKang-Ping Lin, Ratko Magjarevic, Paulo de Carvalho
PublisherSpringer
Pages349-355
Number of pages7
ISBN (Print)9783030306359
DOIs
StatePublished - 1 Jan 2020
Event4th International Conference on Biomedical and Health Informatics, ICBHI 2019 - Taipei, Taiwan, Province of China
Duration: 17 Apr 201920 Apr 2019

Publication series

NameIFMBE Proceedings
Volume74
ISSN (Print)1680-0737
ISSN (Electronic)1433-9277

Conference

Conference4th International Conference on Biomedical and Health Informatics, ICBHI 2019
CountryTaiwan, Province of China
CityTaipei
Period17/04/1920/04/19

Fingerprint

Jitter
Acoustics
Mathematical transformations
Biomarkers
Support vector machines
Classifiers

Keywords

  • Constant Q Transform
  • Dysphonia measurements
  • Mel Frequencies Cepstral Coefficients
  • Parkinson’s disease
  • Support Vector Machine
  • Voice analysis

Cite this

Lopez-Rodríguez, M., García-Vázquez, M. S., Zamudio-Fuentes, L. M., & Ramírez-Acosta, A. (2020). Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods. In K-P. Lin, R. Magjarevic, & P. de Carvalho (Eds.), Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019 (pp. 349-355). (IFMBE Proceedings; Vol. 74). Springer. https://doi.org/10.1007/978-3-030-30636-6_48
Lopez-Rodríguez, Mario ; García-Vázquez, Mireya Sarai ; Zamudio-Fuentes, Luis Miguel ; Ramírez-Acosta, Alejandro. / Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods. Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019. editor / Kang-Ping Lin ; Ratko Magjarevic ; Paulo de Carvalho. Springer, 2020. pp. 349-355 (IFMBE Proceedings).
@inproceedings{135636e37a9943c685db65eefcbbf549,
title = "Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods",
abstract = "Dysphonia is a vocal impediment that appears as a symptom of Parkinson’s disease, and can be used for its diagnosis. Among the important measurements for dysphonia detection are jitter, shimmer, fundamental frequency (F0), Harmonics to noise ratio (HNR) and noise to harmonics ratio (NHR). The frequency space of the speech signal is used to detect these five dysphonia measurements, through this space the acoustic markers jitter, shimmer and F0 are calculated. In this article, an evaluation of the detection of acoustic markers is presented through the mathematical methods of the Constant Q Transform (CQT) and the Mel Frequencies Cepstral Coefficients (MFCC) in speech signals of patients with Parkinson’s disease. The classifier method Support Vector Machine (SVM) is used to detect the Biomarkers. According to the results, the CQT method and MFCC method (57{\%} and 62{\%} precision respectively) which is a promising results for Parkinson’s disease diagnosis by the detection of Dysphonia measurements.",
keywords = "Constant Q Transform, Dysphonia measurements, Mel Frequencies Cepstral Coefficients, Parkinson’s disease, Support Vector Machine, Voice analysis",
author = "Mario Lopez-Rodr{\'i}guez and Garc{\'i}a-V{\'a}zquez, {Mireya Sarai} and Zamudio-Fuentes, {Luis Miguel} and Alejandro Ram{\'i}rez-Acosta",
year = "2020",
month = "1",
day = "1",
doi = "10.1007/978-3-030-30636-6_48",
language = "Ingl{\'e}s",
isbn = "9783030306359",
series = "IFMBE Proceedings",
publisher = "Springer",
pages = "349--355",
editor = "Kang-Ping Lin and Ratko Magjarevic and {de Carvalho}, Paulo",
booktitle = "Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019",

}

Lopez-Rodríguez, M, García-Vázquez, MS, Zamudio-Fuentes, LM & Ramírez-Acosta, A 2020, Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods. in K-P Lin, R Magjarevic & P de Carvalho (eds), Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019. IFMBE Proceedings, vol. 74, Springer, pp. 349-355, 4th International Conference on Biomedical and Health Informatics, ICBHI 2019, Taipei, Taiwan, Province of China, 17/04/19. https://doi.org/10.1007/978-3-030-30636-6_48

Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods. / Lopez-Rodríguez, Mario; García-Vázquez, Mireya Sarai; Zamudio-Fuentes, Luis Miguel; Ramírez-Acosta, Alejandro.

Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019. ed. / Kang-Ping Lin; Ratko Magjarevic; Paulo de Carvalho. Springer, 2020. p. 349-355 (IFMBE Proceedings; Vol. 74).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods

AU - Lopez-Rodríguez, Mario

AU - García-Vázquez, Mireya Sarai

AU - Zamudio-Fuentes, Luis Miguel

AU - Ramírez-Acosta, Alejandro

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Dysphonia is a vocal impediment that appears as a symptom of Parkinson’s disease, and can be used for its diagnosis. Among the important measurements for dysphonia detection are jitter, shimmer, fundamental frequency (F0), Harmonics to noise ratio (HNR) and noise to harmonics ratio (NHR). The frequency space of the speech signal is used to detect these five dysphonia measurements, through this space the acoustic markers jitter, shimmer and F0 are calculated. In this article, an evaluation of the detection of acoustic markers is presented through the mathematical methods of the Constant Q Transform (CQT) and the Mel Frequencies Cepstral Coefficients (MFCC) in speech signals of patients with Parkinson’s disease. The classifier method Support Vector Machine (SVM) is used to detect the Biomarkers. According to the results, the CQT method and MFCC method (57% and 62% precision respectively) which is a promising results for Parkinson’s disease diagnosis by the detection of Dysphonia measurements.

AB - Dysphonia is a vocal impediment that appears as a symptom of Parkinson’s disease, and can be used for its diagnosis. Among the important measurements for dysphonia detection are jitter, shimmer, fundamental frequency (F0), Harmonics to noise ratio (HNR) and noise to harmonics ratio (NHR). The frequency space of the speech signal is used to detect these five dysphonia measurements, through this space the acoustic markers jitter, shimmer and F0 are calculated. In this article, an evaluation of the detection of acoustic markers is presented through the mathematical methods of the Constant Q Transform (CQT) and the Mel Frequencies Cepstral Coefficients (MFCC) in speech signals of patients with Parkinson’s disease. The classifier method Support Vector Machine (SVM) is used to detect the Biomarkers. According to the results, the CQT method and MFCC method (57% and 62% precision respectively) which is a promising results for Parkinson’s disease diagnosis by the detection of Dysphonia measurements.

KW - Constant Q Transform

KW - Dysphonia measurements

KW - Mel Frequencies Cepstral Coefficients

KW - Parkinson’s disease

KW - Support Vector Machine

KW - Voice analysis

UR - http://www.scopus.com/inward/record.url?scp=85075807046&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-30636-6_48

DO - 10.1007/978-3-030-30636-6_48

M3 - Contribución a la conferencia

AN - SCOPUS:85075807046

SN - 9783030306359

T3 - IFMBE Proceedings

SP - 349

EP - 355

BT - Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019

A2 - Lin, Kang-Ping

A2 - Magjarevic, Ratko

A2 - de Carvalho, Paulo

PB - Springer

ER -

Lopez-Rodríguez M, García-Vázquez MS, Zamudio-Fuentes LM, Ramírez-Acosta A. Dysphonia Measurements Detection Using CQT’s and MFCC’s Methods. In Lin K-P, Magjarevic R, de Carvalho P, editors, Future Trends in Biomedical and Health Informatics and Cybersecurity in Medical Devices - Proceedings of the International Conference on Biomedical and Health Informatics, ICBHI 2019. Springer. 2020. p. 349-355. (IFMBE Proceedings). https://doi.org/10.1007/978-3-030-30636-6_48