[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content
Springer Nature Link
Log in

Variable STFT Layered CNN Model for Automated Dysarthria Detection and Severity Assessment Using Raw Speech

  • Published:
Circuits, Systems, and Signal Processing Aims and scope Submit manuscript

A Correction to this article was published on 05 July 2024

This article has been updated

Abstract

This paper presents a novel approach for automated dysarthria detection and severity assessment using a variable short-time Fourier transform layered convolutional neural networks (CNN) model. Dysarthria is a speech disorder characterized by difficulties in articulation, resulting in unclear speech. The model is evaluated on two datasets, TORGO and UA-Speech, consisting of individuals with dysarthria and healthy controls. Various variations of the CNN’s first layer, including spectrogram, log spectrogram, and pre-emphasis filtering (PEF) with and without learnables, are investigated. Notably, the PEF with 5 learnables achieves the highest accuracy in detecting dysarthria and assessing its severity. The study highlights the significance of dataset size, with UA-Speech dataset showing superior performance due to its larger size, enabling better capture of dysarthria severity variations. This research contributes to the advancement of objective dysarthria assessment, aiding in early diagnosis and personalized treatment for individuals with speech disorders.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data Availibility Statement

The open access TORGO data that support the findings of this study is available from the Kaggle repository. The University of Illinois team provided the UA-Speech data upon request. More details about the data are given in Sect. 4.1.

Change history

References

  1. C. Bhat, H. Strik, Automatic assessment of sentence-level dysarthria intelligibility using BLSTM. IEEE J. Select. Top. Signal Process. 14(2), 322–330 (2020)

    Article  Google Scholar 

  2. C. Bhat, B. Vachhani, S.K. Kopparapu, Automatic assessment of dysarthria severity level using audio descriptors, in IEEE International Conference on Acoustics (Speech and Signal Processing (ICASSP) (IEEE, 2017), pp. 5070–5074

  3. M. Carl, E.S. Levy, M. Icht, Speech treatment for Hebrew-speaking adolescents and young adults with developmental dysarthria: a comparison of mSIT and Beatalk. Int. J. Lang. Commun. Disord. 57(3), 660–679 (2022)

    Article  Google Scholar 

  4. H. Chandrashekar, V. Karjigi, N. Sreedevi, Spectro-temporal representation of speech for intelligibility assessment of dysarthria. IEEE J. Sel. Top. Signal Process. 14(2), 390–399 (2019)

    Article  Google Scholar 

  5. H. Chandrashekar, V. Karjigi, N. Sreedevi, Investigation of different time-frequency representations for intelligibility assessment of dysarthric speech. IEEE Trans. Neural Syst. Rehabil. Eng. 28(12), 2880–2889 (2020)

    Article  Google Scholar 

  6. P. Enderby, Disorders of communication: dysarthria. Handb. Clin. Neurol. 110, 273–281 (2013)

    Article  Google Scholar 

  7. J. Fritsch, M. Magimai-Doss, Utterance verification-based dysarthric speech intelligibility assessment using phonetic posterior features. IEEE Signal Process. Lett. 28, 224–228 (2021)

    Article  Google Scholar 

  8. A. Gallardo-Antolín, J.M. Montero, On combining acoustic and modulation spectrograms in an attention LSTM-based system for speech intelligibility level classification. Neurocomputing 456, 49–60 (2021)

    Article  Google Scholar 

  9. S. Gupta, A.T. Patil, M. Purohit et al., Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments. Neural Netw. 139, 105–117 (2021)

    Article  Google Scholar 

  10. A. Hernandez, S. Kim, M. Chung, Prosody-based measures for automatic severity assessment of dysarthric speech. Appl. Sci. 10(19), 6999 (2020)

    Article  Google Scholar 

  11. A.K. Jardine, D. Lin, D. Banjevic, A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mech. Syst. Signal Process. 20(7), 1483–1510 (2006)

    Article  Google Scholar 

  12. A.A. Joshy, R. Rajan, Automated dysarthria severity classification: a study on acoustic features and deep learning techniques. IEEE Trans. Neural Syst. Rehabil. Eng. 30, 1147–1157 (2022)

    Article  Google Scholar 

  13. A.A. Joshy, R. Rajan, Dysarthria severity assessment using squeeze-and-excitation networks. Biomed. Signal Process. Control 82, 1–13 (2023)

    Article  Google Scholar 

  14. A.A. Joshy, R. Rajan, Dysarthria severity classification using multi-head attention and multi-task learning. Speech Commun. 147, 1–11 (2023)

    Article  Google Scholar 

  15. A. Kachhi, A. Therattil, P. Gupta et al, Continuous wavelet transform for severity-level classification of dysarthria, in International Conference on Speech and Computer (Springer, 2022), pp. 312–324

  16. H. Kim, M. Hasegawa-Johnson, A. Perlman et al, Dysarthric speech database for universal access research, in Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH, 2008), pp. 1741–1744

  17. D. Korzekwa, R. Barra-Chicote, B. Kostek et al, Interpretable deep learning model for the detection and reconstruction of dysarthric speech. arXiv:1907.04743 (2019)

  18. S. Latif, J. Qadir, A. Qayyum et al., Speech technology for healthcare: opportunities, challenges, and state of the art. IEEE Rev. Biomed. Eng. 14, 342–356 (2020)

    Article  Google Scholar 

  19. S.K. Maharana, A. Illa, R. Mannem et al., Acoustic-to-articulatory inversion for dysarthric speech by using cross-corpus acoustic-articulatory data, in IEEE International Conference on Acoustics. (Speech and Signal Processing (ICASSP) (IEEE, 2021), pp. 6458–6462

  20. V. Mendoza Ramos, The added value of speech technology in clinical care of patients with dysarthria. Ph.D. thesis, University of Antwerp (2022)

  21. J. Millet, N. Zeghidour, Learning to detect dysarthria from raw speech, in IEEE International Conference on Acoustics. (Speech and Signal Processing (ICASSP) (IEEE, 2019), pp. 5831–5835

  22. N. Narendra, P. Alku, Glottal source information for pathological voice detection. IEEE Access 8, 67745–67755 (2020)

    Article  Google Scholar 

  23. K. Radha, M. Bansal, Automated detection and severity assessment of dysarthria using raw speech, in 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT) (2023a), pp 1–7. https://doi.org/10.1109/ICCCNT56998.2023.10307923

  24. K. Radha, M. Bansal, Feature fusion and ablation analysis in gender identification of preschool children from spontaneous speech. Circuits Syst. Signal Process. 42(10), 6228–6252 (2023)

    Article  Google Scholar 

  25. K. Radha, M. Bansal, Towards modeling raw speech in gender identification of children using sincNet over ERB scale. Int. J. Speech Technol. 26(3), 641–650 (2023)

    Article  Google Scholar 

  26. K. Radha, M. Bansal, R.B. Pachori, Speech and speaker recognition using raw waveform modeling for adult and children’s speech: a comprehensive review. Eng. Appl. Artif. Intell. 131(107), 661 (2024). https://doi.org/10.1016/j.engappai.2023.107661

    Article  Google Scholar 

  27. S. Reza, M.C. Ferreira, J. Machado et al., A customized residual neural network and bi-directional gated recurrent unit-based automatic speech recognition model. Expert Syst. Appl. 215(119), 293 (2023)

    Google Scholar 

  28. P. Roussel, Analysis of cortical activity for the development of brain-computer interfaces for speech. Ph.d. thesis, Université Grenoble Alpes (2021)

  29. F. Rudzicz, A.K. Namasivayam, T. Wolff, The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46, 523–541 (2012)

    Article  Google Scholar 

  30. G. Schu, P. Janbakhshi, I. Kodrasi, On using the UA-Speech and TORGO databases to validate automatic dysarthric speech classification approaches. arXiv:2211.08833 (2022)

  31. S.M. Shabber, M. Bansal, K. Radha, Machine learning-assisted diagnosis of speech disorders: a review of dysarthric speech, in 2023 International Conference on Electrical, Electronics, Communication and Computers (ELEXCOM) (2023a), pp. 1–6. https://doi.org/10.1109/ELEXCOM58812.2023.10370116

  32. S.M. Shabber, M. Bansal, K. Radha, A review and classification of amyotrophic lateral sclerosis with speech as a biomarker. in 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT) (2023b), pp 1–7. https://doi.org/10.1109/ICCCNT56998.2023.10308048

  33. B. Suhas, D. Patel, N.R. Koluguri et al, Comparison of speech tasks and recording devices for voice based automatic classification of healthy subjects and patients with amyotrophic lateral sclerosis. (INTERSPEECH, 2019), pp. 4564–4568

  34. B. Suhas, J. Mallela, A. Illa et al, Speech task based automatic classification of als and parkinson’s disease and their severity using log mel spectrograms, in 2020 International Conference on Signal Processing and Communications (SPCOM) (IEEE, 2020), pp. 1–5

  35. N. Tavabi, D. Stück, A. Signorini et al., Cognitive digital biomarkers from automated transcription of spoken language. J. Prevent. Alzheimer’s Dis. 9(4), 791–800 (2022)

    Google Scholar 

  36. M.J. Vansteensel, E. Klein, G. van Thiel et al., Towards clinical application of implantable brain-computer interfaces for people with late-stage ALS: medical and ethical considerations. J. Neurol. 270(3), 1323–1336 (2023)

    Article  Google Scholar 

  37. P.W. Wong, N. Moayeri, C. Herley, Optimum pre-and post-filters for robust scalar quantization, in Proceedings of Data Compression Conference-DCC’96 (IEEE, 2022), pp. 240–249

  38. K.M. Yorkston, Treatment efficacy: dysarthria. J. Speech Lang. Hear. Res. 39(5), S46–S57 (1996)

    Article  Google Scholar 

  39. Z. Yue, E. Loweimi, H. Christensen, et al., Dysarthric speech recognition from raw waveform with parametric CNNs, in Proceedings of INTERSPEECH 2022. ISCA-INST SPEECH COMMUNICATION ASSOC (2022)

Download references

Funding

This research received no external funding.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Kanuru, Andhra Pradesh, 520007, India

    Kodali Radha & Venkata Rao Dhulipalla

  2. Electronics and Communication Engineering, Indian Institute of Information Technology Sonepat, IITD Techno Park, Sonipat, Haryana, 131001, India

    Mohan Bansal

Authors
  1. Kodali Radha
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohan Bansal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Venkata Rao Dhulipalla
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kodali Radha.

Ethics declarations

Conflict of interest

The authors declare no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original online version of this article was revised: and the incorrect name of author Venkata Rao Dhulipalla has been corrected.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Radha, K., Bansal, M. & Dhulipalla, V.R. Variable STFT Layered CNN Model for Automated Dysarthria Detection and Severity Assessment Using Raw Speech. Circuits Syst Signal Process 43, 3261–3278 (2024). https://doi.org/10.1007/s00034-024-02611-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00034-024-02611-7

Keywords

Search

Navigation