Abstract
The clinical assessment of speech abnormalities in Cerebellar Ataxia (CA) is time-consuming and inconsistent. We have developed an automated objective system to quantify CA severity and thereby facilitate remote monitoring and optimisation of therapeutic interventions. A quantitative acoustic assessment could prove to be a viable biomarker for this purpose. Our study explores the use of phase-based cepstral features extracted from the modified group delay function as a complement to the features obtained from the magnitude cepstrum. We selected a combination of 15 acoustic measurements using RELIEF feature selection algorithm during the feature optimisation process. These features were used to segregate ataxic speakers from normal speakers (controls) and objectively assess them based on their severity. The effectiveness of our study has been experimentally evaluated through a clinical study involving 42 patients diagnosed with CA and 23 age-matched controls. A radial basis function kernel based support vector machine (SVM) classifier achieved a classification accuracy of 84.6% in CA–Control discrimination [area under the ROC curve (AUC) of 0.97] and 74% in the modified 3-level CA severity estimation (AUC of 0.90) deduced from the clinical ratings. The strong classification ability of selected features and the SVM model supports this scheme’s suitability for monitoring CA related speech motor abnormalities.
Similar content being viewed by others
References
Ackermann, H. and I. Hertrich. Speech rate and rhythm in cerebellar dysarthria: an acoustic analysis of syllabic timing. Folia Phoniatr. Logop. 46(2):70–78, 1994.
Ali, Z., M. Alsulaiman, G. Muhammad, I. Elamvazuthi, and T. A. Mesallam. Vocal fold disorder detection based on continuous speech by using MFCC and GMM. In: 2013 7th IEEE GCC Conference and Exhibition (GCC), November. IEEE, 2013, pp. 292–297.
Alim, S. A. and N. K. A. Rashid. Some commonly used speech feature extraction algorithms. In: From Natural to Artificial Intelligence-Algorithms and Applications. London: IntechOpen, 2018.
Bäckström, T. Speech Coding: With Code-Excited Linear Prediction. Cham: Springer, 2017.
Benba, A., A. Jilbab, A. Hammouch, and S. Sandabad. Voiceprints analysis using MFCC and SVM for detecting patients with Parkinson’s disease. In: 2015 International Conference on Electrical and Information Technologies (ICEIT), March. IEEE, 2015, pp. 300–304.
Berger, Y. G. A jackknife variance estimator for unistage stratified samples with unequal probabilities. Biometrika 94(4):953–964, 2007.
Boes, C. J. History of neurologic examination books. Bayl. Univ. Med. Center Proc. 28(2):172–179, 2015.
Breathnach, C. S. Sir Gordon Holmes. Med. Hist. 19(2):194–200, 1975.
Brendel, B., H. Ackermann, D. Berg, T. Lindig, T. Schölderle, L. Schöls, M. Synofzik, and W. Ziegler. Friedreich ataxia: dysarthria profile and clinical data. Cerebellum 12(4):475–484, 2013.
Brendel, B., M. Synofzik, H. Ackermann, T. Lindig, T. Schölderle, L. Schöls, and W. Ziegler. Comparing speech characteristics in spinocerebellar ataxias type 3 and type 6 with Friedreich ataxia. J. Neurol. 262(1):21–26, 2015.
De Boer, E. A note on phase distortion and hearing. Acustica 11:182–184, 1961.
Diener, H. C. and J. Dichgans. Pathophysiology of cerebellar ataxia. Mov. Disord. Off. J. Mov. Disord. Soc. 7(2):95–109, 1992.
Fine, E. J., C. C. Ionita, and L. Lohr. The history of the development of the cerebellar examination. Semin. Neurol. 22(04):375–384, 2002.
Frail, R., J. I. Godino-Llorente, N. Saenz-Lechon, V. Osma-Ruiz, and C. Fredouille. MFCC-based remote pathology detection on speech transmitted through the telephone channel. In: Proceedings of Biosignals, 2009.
Fraile, R., J. I. Godino-Llorente, N. Sáenz-Lechón, V. Osma-Ruiz, and P. Gómez-Vilda. Use of cepstrum-based parameters for automatic pathology detection on speech. Proc. Biosignals’ 08 1:85–91, 2008.
Fu, Z., G. Lu, K. M. Ting, and D. Zhang. Optimizing cepstral features for audio classification. In: Twenty-Third International Joint Conference on Artificial Intelligence, June 2013.
Furui, S. Speaker recognition in smart environments. In: Human-Centric Interfaces for Ambient Intelligence. Cambridge: Academic, pp. 163–184, 2010.
Gerkmann, T., M. Krawczyk-Becker and J. Le Roux. Phase processing for single-channel speech enhancement: history and recent advances. IEEE Signal Process. Mag. 32(2):55–66, 2015.
Hegde, R. M., H. A. Murthy, and V. R. R. Gadde. Significance of the modified group delay feature in speech recognition. IEEE Trans. Audio Speech Lang. Process. 15(1):190–202, 2006.
Jafari, A. Classification of Parkinson’s disease patients using nonlinear phonetic features and Mel-frequency cepstral analysis. Biomed. Eng. Appl. Basis Commun. 25(04):1350001, 2013.
Jannetts, S. and A. Lowit. Cepstral analysis of hypokinetic and ataxic voices: correlations with perceptual and other acoustic measures. J. Voice 28(6):673–680, 2014.
Jelliffe, S. E., and W. A. White. Diseases of the Nervous System: A Text-Book of Neurology and Psychiatry. Philadelphia: Lea & Febiger, 1923.
Kashyap, B., P. N. Pathirana, M. Horne, L. Power, and D. Szmulewicz. Identification of cerebellar dysarthria with SISO characterisation. In: 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE), October. IEEE, 2017, pp. 479–485.
Kashyap, B., P. N. Pathirana, M. Horne, L. Power, and D. Szmulewicz. Quantitative assessment of syllabic timing deficits in ataxic dysarthria. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), July. IEEE, 2018, pp. 425–428.
Kent, R. D., J. F. Kent, J. R. Duffy, J. E. Thomas, G. Weismer, and S. Stuntebeck. Ataxic dysarthria. J. Speech Lang. Hear. Res. 43(5):1275–1289, 2000.
Laitinen, M. V., S. Disch, and V. Pulkki. Sensitivity of human hearing to changes in phase spectrum. J. Audio Eng. Soc. 61(11):860–877, 2013.
Liu, H. and H. Motoda. Computational Methods of Feature Selection. Boca Raton: CRC Press, 2007.
Luna-Webb, S. Comparison of Acoustic Measures in Discriminating Between Those with Friedreich’s Ataxia and Neurologically Normal Peers, 2015.
Murthy, H. A. and V. Gadde. The modified group delay function and its application to phoneme recognition. In: 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings (ICASSP’03), April, Vol. 1. IEEE, 2003, p. I-68.
Ohm, G. S. On the definition of sound, together with the theory of the siren and similar sound-forming devices linked to it. Ann. Phys. 135(8):513–565, 1843.
Paliwal, K. K. and L. Alsteris. Usefulness of phase spectrum in human speech perception. In: Eighth European Conference on Speech Communication and Technology, 2003.
Patterson, R. D. A pulse ribbon model of monaural phase perception. J. Acoust. Soc. Am. 82(5)1560–1586, 1987.
Peng, H., F. Long, and C. Ding. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans. Pattern Anal. Mach. Intell. 27(8):1226-1238, 2005.
Plomp, R. and H. J. Steeneken. Effect of phase on the timbre of complex tones. J. Acoust. Soc. Am. 46(2B):409–421, 1969.
Rovini, E., C. Maremmani, A. Moschetti, D. Esposito, and F. Cavallo. Comparative motor pre-clinical assessment in Parkinson’s disease using supervised machine learning approaches. Ann. Biomed. Eng. 46(12):2057–2068, 2018.
Schalling, E., B. Hammarberg, and L. Hartelius. Perceptual and acoustic analysis of speech in individuals with spinocerebellar ataxia (SCA). Logop. Phoniatr. Vocol. 32(1):31–46, 2007.
Schalling, E., B. Hammarberg, and L. Hartelius. A longitudinal study of dysarthria in spinocerebellar ataxia (SCA): aspects of articulation, prosody, and voice. J. Med. Speech–Lang. Pathol. 16(2):103–118, 2008.
Schmitz-Hübsch, T., S. T. Du Montcel, L. Baliko, J. Berciano, S. Boesch, C. Depondt, P. Giunti, C. Globas, J. Infante, J. S. Kang, and B. Kremer. Scale for the assessment and rating of ataxia: development of a new clinical scale. Neurology 66(11):1717–1720, 2006.
Schroeder, M. R. New results concerning monaural phase sensitivity. J. Acoust. Soc. Am. 31(11):1579, 1959.
Seasholtz, M.B. and B. Kowalski, The parsimony principle applied to multivariate calibration. Analytica Chimica Acta, 277(2), pp.165-177, 1993.
Vikram, C. M. and K. Umarani. Pathological voice analysis to detect neurological disorders using MFCC and SVM. Int. J. Adv. Electr. Electron. Eng. 2(4):87–91, 2013.
Vogel, A. P., N. Rommel, A. Oettinger, L. H. Stoll, E. M. Kraus, C. Gagnon, M. Horger, P. Krumm, D. Timmann, E. Storey, and L. Schöls. Coordination and timing deficits in speech and swallowing in autosomal recessive spastic ataxia of Charlevoix–Saguenay (ARSACS). J. Neurol. 265(9):2060–2070, 2018.
Wu, Z., E. S. Chng, and H. Li. Detecting converted speech and natural speech for anti-spoofing attack in speaker recognition. In: Thirteenth Annual Conference of the International Speech Communication Association, 2012.
Yu, J.S., A.Y. Xue, E.E. Redei, and N. Bagheri, A support vector machine model provides an accurate transcript-level-based diagnostic for major depressive disorder. Translational psychiatry, 6(10), p.e931, 2016.
Acknowledgments
This research is supported by the Royal Victorian Eye and Ear Hospital (RVEEH), the Florey Institute of Neuroscience and Mental Health, Melbourne, Australia through the National Health and Medical Research Council (NHMRC, Grant GNT1101304 and APP1129595) and CSIRO Data61.
Author information
Authors and Affiliations
Corresponding author
Additional information
Associate Editor Eiji Tanaka oversaw the review of this article.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kashyap, B., Pathirana, P.N., Horne, M. et al. Quantitative Assessment of Speech in Cerebellar Ataxia Using Magnitude and Phase Based Cepstrum. Ann Biomed Eng 48, 1322–1336 (2020). https://doi.org/10.1007/s10439-020-02455-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10439-020-02455-7