[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
article

Exploring similarity-based classification of larynx disorders from human voice

Published: 01 June 2012 Publication History

Abstract

In this paper identification of laryngeal disorders using cepstral parameters of human voice is researched. Mel-frequency cepstral coefficients (MFCCs), extracted from audio recordings of patient's voice, are further approximated, using various strategies (sampling, averaging, and clustering by Gaussian mixture model). The effectiveness of similarity-based classification techniques in categorizing such pre-processed data into normal voice, nodular, and diffuse vocal fold lesion classes is explored and schemes to combine binary decisions of support vector machines (SVMs) are evaluated. Most practiced RBF kernel was compared to several constructed custom kernels: (i) a sequence kernel, defined over a pair of matrices, rather than over a pair of vectors and calculating the kernelized principal angle (KPA) between subspaces; (ii) a simple supervector kernel using only means of patient's GMM; (iii) two distance kernels, specifically tailored to exploit covariance matrices of GMM and using the approximation of the Kullback-Leibler divergence from the Monte-Carlo sampling (KL-MCS), and the Kullback-Leibler divergence combined with the Earth mover's distance (KL-EMD) as similarity metrics. The sequence kernel and the distance kernels both outperformed the popular RBF kernel, but the difference is statistically significant only in the distance kernels case. When tested on voice recordings, collected from 410 subjects (130 normal voice, 140 diffuse, and 140 nodular vocal fold lesions), the KL-MCS kernel, using GMM with full covariance matrices, and the KL-EMD kernel, using GMM with diagonal covariance matrices, provided the best overall performance. In most cases, SVM reached higher accuracy than least squares SVM, except for common binary classification using distance kernels. The results indicate that features, modeled with GMM, and kernel methods, exploiting this information, is an interesting fusion of generative (probabilistic) and discriminative (hyperplane) models for similarity-based classification.

References

[1]
Springer Handbook of Speech Processing. Springer-Verlag, New York, Inc., Secaucus, NJ, USA.
[2]
Similarity-based classification: concepts and algorithms. Journal of Machine Learning Research. v10. 747-776.
[3]
Doremalen, J. 2007. Hierarchical temporal memory networks for spoken digit recognition, Ph.D. thesis, Radboud University Nijmegen, Department of Language & Speech.
[4]
Dubnov, S., Yazdani, M. 2008. Computer audition toolbox (catbox). URL <http://cosmal.ucsd.edu/cal/projects/CATbox>.
[5]
Automated speech analysis applied to laryngeal disease categorization. Computer Methods and Programs in Biomedicine. v91. 36-47.
[6]
Support vector machines applied to the detection of voice disorders. In: Faundez-Zanuy, M., Janer, L., Esposito, A., Satue-Villar, A., Roure, J., Espinosa-Duro, V. (Eds.), Lecture Notes in Computer Science, vol. 3817. Springer, Berlin / Heidelberg. pp. 219-230.
[7]
Nonparametric speaker recognition method using Earth mover's distance. IEICE Transactions on Information and Systems. vE89-D. 1074-1081.
[8]
Levina, E., Bickel, P. 2001. The Earth mover's distance is the mallows distance: some insights from statistics. In: Proceedings of the 8th IEEE International Conference on Computer Vision (ICCV), vol. 2, pp. 251-256.
[9]
Markaki, M.E., Stylianou, Y., Arias-Londoño, J.D., Godino-Llorente, J.I. 2010. Dysphonia detection based on modulation spectral features and cepstral coefficients. In: Proceedings of the 35th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5162-5165.
[10]
Applying SVMS and weight-based factor analysis to unsupervised adaptation for speaker verification. Computer Speech & Language. v25 i2. 327-340.
[11]
Pampalk, E. 2004 A matlab toolbox to compute music similarity from audio. In: Proceedings of the 5th International Conference on Music Information Retrieval (ISMIR).
[12]
Pouchoulin, G., Fredouille, C., Bonastre, J.-F., Ghio, A., Giovanni, A. 2007. Frequency study for the characterization of the dysphonic voices. In: Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech), p. 11981201.
[13]
Least squares support vector machine classifiers. Neural Processing Letters. v9 i3. 293-300.
[14]
Similarity, separability, and the triangle inequality. Psychological Review. v89 i2. 123-154.
[15]
Wang, X., Zhang, J., Yan, Y., 2011. Discrimination between pathological and normal voices using GMM-SVM approach., Journal of Voice. <http://www.jvoice.org/article/S0892-1997(09)00119-2/abstract>.
[16]
Weston, J., Sinz, F. 2006. Matlab toolbox for kernel methods: Spider. URL <http://www.kyb.tuebingen.mpg.de/bs/people/spider/>.
[17]
Weston, J., Watkins, C. 1999. Support vector machines for multi-class pattern recognition. In: Proceedings of the 7th European Symposium on Artificial Neural Networks (ESANN).
[18]
Learning over sets using kernel principal angles. Journal of Machine Learning Research. v4. 913-931.
[19]
Class-incremental generalized discriminant analysis. Neural Computations. v18 i4. 979-1006.

Cited By

View all
  • (2020)Wavelet sub-band features for voice disorder detection and classificationMultimedia Tools and Applications10.1007/s11042-020-09424-179:39-40(28499-28523)Online publication date: 1-Oct-2020
  • (2015)Fusing voice and query data for non-invasive detection of laryngeal disordersExpert Systems with Applications: An International Journal10.1016/j.eswa.2015.07.00142:22(8445-8453)Online publication date: 1-Dec-2015
  1. Exploring similarity-based classification of larynx disorders from human voice

      Recommendations

      Comments

      Please enable JavaScript to view thecomments powered by Disqus.

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)0
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 20 Dec 2024

      Other Metrics

      Citations

      Cited By

      View all
      • (2020)Wavelet sub-band features for voice disorder detection and classificationMultimedia Tools and Applications10.1007/s11042-020-09424-179:39-40(28499-28523)Online publication date: 1-Oct-2020
      • (2015)Fusing voice and query data for non-invasive detection of laryngeal disordersExpert Systems with Applications: An International Journal10.1016/j.eswa.2015.07.00142:22(8445-8453)Online publication date: 1-Dec-2015

      View Options

      View options

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media