Impact of noise on the performance of automatic systems for vocal fold lesions detection

• Autorzy: Madruga Mario , Campos-Roca Yolanda , Pérez Carlos J.

Identyfikatory

DOI

10.1016/j.bbe.2021.07.001

• Języki publikacji: EN

Abstrakty

EN

Automatic voice condition analysis systems have been developed to automatically discriminate pathological voices from healthy ones in the context of two disorders related to exudative lesions of Reinke’s space: nodules and Reinke’s edema. The systems are based on acoustic features, extracted from sustained vowel recordings. Reduced subsets of features have been obtained from a larger set by a feature selection algorithm based on Whale Optimization in combination with Support Vector Machine classification. Robustness of the proposed systems is assessed by adding noise of two different types (synthetic white noise and actual noise recorded in a clinical environment) to corrupt the speech signals. Two speech databases were used for this investigation: the Massachusetts Eye and Ear Infirmary (MEEI) database and a second one specifically collected in Hospital San Pedro de Alcántara (Cáceres, Spain) for the scope of this work (UEX-Voice database). The results show that the prediction performance of the detection systems appreciably decrease when moving from MEEI to a database recorded in more realistic conditions. For both pathologies, the prediction performance declines under noisy conditions, being the effect of white noise more pronounced than the effect of noise recorded in the clinical environment.

Słowa kluczowe

EN

acoustic features; computer aided diagnosis; Reinke’s edema; noise robustness; voice disorders

PL

cechy akustyczne; diagnoza wspomagana komputerowo; zaburzenia głosu

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 3
• Strony: 1039--1056
• Opis fizyczny: Bibliogr. 50 poz., rys., tab., wykr.

Twórcy

autor

Madruga Mario

• Departamento de Matemáticas, Universidad de Extremadura, Spain; Facultad de Veterinaria, Avenida de la Universidad S/N, Cáceres, Spain

autor

Campos-Roca Yolanda

• Departamento de Tecnología de los Computadores y las Comunicaciones, Universidad de Extremadura, Spain

autor

Pérez Carlos J.

• Departamento de Matemáticas, Universidad de Extremadura, Spain

Bibliografia

• [1] Rufo M, Martín J, Pérez C, Paniagua S. A Bayesian decision analysis approach to assess voice disorder risks by using acoustic features. Biometr J 2019;61(3):503–13.
• [2] Hantzakos A, Remacle M, Dikkers FG, Degols JC, Delos M, Friedrich G, Giovanni A, Rasmussen N. Exudative lesions of Reinke’s space: a terminology proposal. Eur Arch Otorhinolaryngol 2009;266(6):869.
• [3] Echternach M, Döllinger M, Köberlein M, Kuranova L, Gellrich D, Kainz M. Vocal fold oscillation pattern changes related to loudness in patients with vocal fold mass lesions. J Otolaryngol Head Neck Surg 2020;49(1):1–9.
• [4] Sataloff RT. Clinical assessment of voice. Plural publishing; 2017.
• [5] Gómez-García J, Moro-Velázquez L, Godino-Llorente J. On the design of automatic voice condition analysis systems. Part I: Review of concepts and an insight to the state of the art. Biomed Sig Process Control 2019;51:181–99.
• [6] Kowalska-Taczanowska R, Friedman A, Koziorowski D. Parkinson’s disease or atypical parkinsonism? The importance of acoustic voice analysis in differential diagnosis of speech disorders. Brain Behav 2020;10(8) e01700.
• [7] Paniagua M, Pérez C, Calle-Alonso F, Salazar C. An acoustic-signal-based preventive program for university lecturers’ vocal health. J Voice 2018;34(1):88–99.
• [8] Kadiri SR, Alku P. Analysis and detection of pathological voice using glottal source features. IEEE J Select Top Sig Process 2019;14(2):367–79.
• [9] Hegde S, Shetty S, Rai S, Dodderi T. A survey on machine learning approaches for automatic detection of voice disorders. J Voice 2019;33(6):947–58.
• [10] Orozco-Arroyave JR, Belalcazar-Bolanos EA, Arias-Londoño JD, Vargas-Bonilla JF, Skodda S, Rusz J, Daqrouq K, Hönig F, Nöth E. Characterization methods for the detection of multiple voice disorders: neurological, functional, and laryngeal diseases. IEEE J Biomed Health Inf 2015;19 (6):1820–8.
• [11] J. Tang, S. Alelyani, and H. Liu, Feature selection for classification: A review, Data classification: Algorithms and Applications, 2014:37–64.
• [12] Mirjalili S, Lewis A. The whale optimization algorithm. Adv Eng Softw 2016;95:51–67.
• [13] Canayaz M, Demir M. Feature selection with the whale optimization algorithm and artificial neural network. In: 2017 International Artificial Intelligence and Data Processing Symposium (IDAP).
• [14] Mafarja M, Mirjalili S. Whale optimization approaches for wrapper feature selection. Appl Softw Comput 2018;62:441–53.
• [15] Massachusetts Eye and Ear Infirmary, Voice disorders database, Version 1.03 (cd-rom), Lincoln Park, NJ: Kay Elemetrics Corporation; 1994.
• [16] Travieso CM, Alonso JB, Orozco-Arroyave JR, Solé-Casals J, Gallego-Jutglà E. Automatic detection of laryngeal pathologies in running speech based on the HMM transformation of the nonlinear dynamics. Int Conf Nonlinear Speech Process 2013.
• [17] Arias-Vergara T, Vásquez-Correa J, Orozco-Arroyave J, Nöth E. Speaker models for monitoring Parkinson’s disease progression considering different communication channels and acoustic conditions. Speech Commun 2018;101:11–25.
• [18] Tsanas A, Little M, Ramig L. Remote assessment of parkinson’s disease symptom severity using the simulated cellular mobile telephone Network. IEEE Access. 2021.
• [19] Cesari U, De Pietro G, Marciano E, Niri C, Sannino G, Verde L. Voice disorder detection via an m-Health system: Design and results of a clinical study to evaluate Vox4Health. BioMed Res Int 2018;2018.
• [20] Saggio G, Costantini G. Worldwide healthy adult voice baseline parameters: a comprehensive review. J Voice 2020.
• [21] Deliyski DD, Shaw HS, Evans MK. Adverse effects of environmental noise on acoustic voice quality measurements. J Voice 2005;19(1):15–28.
• [22] van der Woerd B, Wu M, Parsa V, Doyle P, Fung K. Evaluation of Acoustic Analyses of Voice in Nonoptimized Conditions. J Speech Language Hearing Res 2020;63(12):3991–9.
• [23] Madruga M, Campos-Roca Y, Pérez CJ. Robustness assessment of automatic Reinke’s edema diagnosis systems. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
• [24] Vásquez-Correa JC, Serra J, Orozco-Arroyave JR, Vargas-Bonilla JF, Nöth E. Effect of acoustic conditions on algorithms to detect Parkinson’s disease from speech. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2017.
• [25] Madruga M, Campos-Roca Y, Pérez C. Multicondition training for noise-robust detection of benign vocal fold lesions from recorded speech. IEEE Access. 2020.
• [26] Fraile R, Godino-Llorente JI. Cepstral peak prominence: A comprehensive analysis. Biomed Signal Process Control 2014;14:42–54.
• [27] Tsanas A. Acoustic analysis toolkit for biomedical speech signal processing: concepts and algorithms. Models Anal Vocal Emiss Biomed Appl 2013;2:37–40.
• [28] Alves M, Silva G, Bispo B, Dajer M, Rodrigues P. Voice disorders detection through multiband cepstral features of sustained vowel. J Voice 2021.
• [29] Henríquez P, Alonso JB, Ferrer MA, Travieso CM, Godino-Llorente JI, Díaz-de María F. Characterization of healthy and pathological voice through measures based on nonlinear dynamics. IEEE Trans Audio Speech Language Process 2009;17 (6):1186–1195.
• [30] Ihlen EAF. Introduction to multifractal detrended fluctuation analysis in matlab. Front Physiol 2012;3:141.
• [31] Islam R, Tarique M, Abdel-Raheem E. A survey on signal processing based pathological voice detection techniques. IEEE Access 2020;8:66749–76.
• [32] Riedl M, Müller A, Wessel N. Practical considerations of permutation entropy. Eur Phys J Spec Top 2013;222(2):249–62.
• [33] Orozco JR, Vargas JF, Alonso JB, Ferrer MA, Travieso CM, Henríquez P. Voice pathology detection in continuous speech using nonlinear dynamics. In: 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).
• [34] Behrman A. Speech and voice science. Plural publishing; 2017.
• [35] Hixon TJ, Weismer G, Hoit JD. Preclinical speech science: Anatomy, physiology, acoustics, and perception. Plural Publishing; 2018.
• [36] Van Houtte E, Van Lierde K, D’haeseleer E, Claeys S. The prevalence of laryngeal pathology in a treatment-seeking population with dysphonia. Laryngoscope 2010;120(2):306-312.
• [37] Brückl M, Ghio A, Alain, Viallet F. Measurement of tremor in the voices of speakers with Parkinson’s disease. Proc Comput Sci 2018;128:47–54.
• [38] Illner V, Sovka P, Rusz J. Validation of freely-available pitch detection algorithms across various noise levels in assessing speech captured by smartphone in Parkinson’s disease. Biomed Signal Process Control 2020;58 101831.
• [39] Tsanas A. Accurate telemonitoring of Parkinson’s disease symptom severity using nonlinear speech signal processing and statistical machine learning, Ph.D. dissertation, Oxford University, UK, 2012.
• [40] Tsanas A, Gómez-Vilda P. Novel robust decision support tool assisting early diagnosis of pathological voices using acoustic analysis of sustained vowels, in Multidisciplinary Conference of Users of Voice, Speech and Singing (JVHC 13); 2013.
• [41] Despotovic V, Skovranek T, Schommer C. Speech based estimation of Parkinson’s disease using Gaussian processes and automatic relevance determination. Neurocomputing 2020;401:173–81.
• [42] Luan F, Cai Z, Wu S, Liu S, He Y. Optimizing the low-carbon flexible job shop scheduling problem with discrete whale optimization algorithm. Mathematics 2019;7(8):688.
• [43] Arias-Londoño J, Godino-Llorente J, Sáenz-Lechón N, Osma-Ruiz V, Víctor, Castellanos-Domínguez G. An improved method for voice pathology detection by means of a HMM-based feature space transformation. Pattern Recognit 2010;43 (9):3100–12.
• [44] Daoudi K, Bertrac B. On classification between normal and pathological voices using the MEEI-KayPentax database: Issues and consequences. In: Fifteenth Annual Conference of the International Speech Communication Association.
• [45] Sataloff RT, Chowdhury F, Portnoy JE, Hawkshaw MJ, Joglekar S. Surgical techniques in otolaryngology-head & Neck Surgery: Laryngeal Surgery. JP Medical Ltd 2013.
• [46] Syed S, Rashid M, Hussain S. Meta-analysis of voice disorders databases and applied machine learning techniques. Math Biosci Eng: MBE 2020;17(6):7958–79.
• [47] Fang S, Tsao Y, Hsiao M, Chen J, Lai Y, Lin F, Wang C. Detection of pathological voice using cepstrum vectors: A deep learning approach. J Voice 2019;33(5):634–41.
• [48] Alhussein M, Muhammad G. Voice pathology detection using deep learning on mobile healthcare framework. IEEE Access 2018;6:41034–41.
• [49] Harar P, Galaz Z, Alonso-Hernandez Jesus B, Mekyska J, Burget R, Smekal Z. Towards robust voice pathology detection. Neural Comput Appl 2018:1–11.
• [50] Karan B, Sahu S, Mahto K. Parkinson disease prediction using intrinsic mode function based features from speech signal. Biocybern Biomed Eng 2020;40(1):249–64.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).