{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:55:20Z","timestamp":1776444920084,"version":"3.51.2"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s10772-024-10098-5","type":"journal-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T13:03:06Z","timestamp":1712149386000},"page":"255-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Hyperkinetic Dysarthria voice abnormalities: a neural network solution for text translation"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7926-9245","authenticated-orcid":false,"given":"Antor Mahamudul","family":"Hashan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaganov Roman","family":"Dmitrievich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6929-5473","authenticated-orcid":false,"given":"Melnikov Alexander","family":"Valerievich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorokh Danila","family":"Vasilyevich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3662-1039","authenticated-orcid":false,"given":"Khlebnikov Nikolai","family":"Alexandrovich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7370-9947","authenticated-orcid":false,"given":"Boris Andreevich","family":"Bredikhin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,4,3]]},"reference":[{"key":"10098_CR1","doi-asserted-by":"publisher","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","volume":"10","author":"Z Abdul","year":"2022","unstructured":"Abdul, Z., Kh, & Al-Talabani, A. K. (2022). Mel frequency Cepstral coefficient and its applications: A review. IEEE Access: Practical Innovations, Open Solutions, 10, 122136\u2013122158. https:\/\/doi.org\/10.1109\/ACCESS.2022.3223444","journal-title":"Ieee Access: Practical Innovations, Open Solutions"},{"key":"10098_CR2","unstructured":"Agarap, A. F. (2019). Deep Learning using Rectified Linear Units (ReLU). arXiv:1803.08375 [Cs, Stat]. http:\/\/arxiv.org\/abs\/1803.08375"},{"issue":"8","key":"10098_CR3","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1049\/sil2.12057","volume":"15","author":"HA Alsayadi","year":"2021","unstructured":"Alsayadi, H. A., Abdelhamid, A. A., Hegazy, I., & Fayed, Z. T. (2021). Arabic speech recognition using end-to\u2010end deep learning. IET Signal Processing, 15(8), 521\u2013534. https:\/\/doi.org\/10.1049\/sil2.12057","journal-title":"IET Signal Processing"},{"key":"10098_CR4","doi-asserted-by":"publisher","unstructured":"Andrusenko, A., Laptev, A., & Medennikov, I. (2020). Exploration of end-to-end ASR for OpenSTT -- Russian open speech-to-text dataset. https:\/\/doi.org\/10.48550\/ARXIV.2006.08274","DOI":"10.48550\/ARXIV.2006.08274"},{"key":"10098_CR6","doi-asserted-by":"publisher","unstructured":"Ashraf, A., Mumtaz, N., & Saqulain, G. (2023). Treatment approaches to motor speech disorders: A step towards evidence based practice. Pakistan Journal of Medical Sciences, 40(3). https:\/\/doi.org\/10.12669\/pjms.40.3.8096","DOI":"10.12669\/pjms.40.3.8096"},{"key":"10098_CR7","unstructured":"Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization (arXiv:1607.06450). arXiv. http:\/\/arxiv.org\/abs\/1607.06450"},{"key":"10098_CR8","doi-asserted-by":"publisher","unstructured":"Bredikhin, B. A., Antor, M. H., Khlebnikov, N. A., Melnikov, A. V., & Bachurin, M. V. (2024). Dysarthria speech recognition by phonemes using hidden Markov models. \u041c\u041e\u0414\u0415\u041b\u0418\u0420\u041e\u0412\u0410\u041d\u0418\u0415 \u041e\u041f\u0422\u0418\u041c\u0418\u0417\u0410\u0426\u0418\u042f \u0418 \u0418\u041d\u0424\u041e\u0420\u041c\u0410\u0426\u0418\u041e\u041d\u041d\u042b\u0415 \u0422\u0415\u0425\u041d\u041e\u041b\u041e\u0413\u0418\u0418, Page2. https:\/\/doi.org\/10.26102\/2310-6018\/2024.44.1.002","DOI":"10.26102\/2310-6018\/2024.44.1.002"},{"key":"10098_CR9","unstructured":"de Br\u00e9bisson, A. (2016). P. Vincent (Ed.), An exploration of Softmax alternatives belonging to the spherical loss family. arXiv arXiv:1511.05042 http:\/\/arxiv.org\/abs\/1511.05042"},{"issue":"11 Suppl 5","key":"10098_CR10","first-page":"S21","volume":"54","author":"MC de Rijk","year":"2000","unstructured":"de Rijk, M. C., Launer, L. J., Berger, K., Breteler, M. M., Dartigues, J. F., Baldereschi, M., Fratiglioni, L., Lobo, A., Martinez-Lage, J., Trenkwalder, C., & Hofman, A. (2000). Prevalence of Parkinson\u2019s disease in Europe: A collaborative study of population-based cohorts. Neurologic diseases in the elderly research group. Neurology, 54(11 Suppl 5), S21\u201323.","journal-title":"Neurology"},{"issue":"3","key":"10098_CR11","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1016\/j.dsp.2009.10.004","volume":"20","author":"G Dede","year":"2010","unstructured":"Dede, G., & Sazl\u0131, M. H. (2010). Speech recognition with artificial neural networks. Digital Signal Processing, 20(3), 763\u2013768. https:\/\/doi.org\/10.1016\/j.dsp.2009.10.004","journal-title":"Digital Signal Processing"},{"key":"10098_CR12","doi-asserted-by":"publisher","unstructured":"Espa\u00f1a-Bonet, C., & Fonollosa, J. A. R. (2016). Automatic speech recognition with deep neural networks for impaired speech. In A. Abad, A. Ortega, A. Teixeira, C. Garc\u00eda Mateo, C. D. Mart\u00ednez Hinarejos, F. Perdig\u00e3o, F. Batista, & N. Mamede (Eds.), Advances in speech and language technologies for Iberian languages (Vol. 10077, pp. 97\u2013107). Springer. https:\/\/doi.org\/10.1007\/978-3-319-49169-1_10","DOI":"10.1007\/978-3-319-49169-1_10"},{"key":"10098_CR13","doi-asserted-by":"publisher","DOI":"10.13052\/jmm1550-4646.1869","author":"S Girirajan","year":"2022","unstructured":"Girirajan, S., & Pandian, A. (2022). Offline automatic speech recognition system based on bidirectional gated recurrent unit (Bi-GRU) with convolution neural network. Journal of Mobile Multimedia. https:\/\/doi.org\/10.13052\/jmm1550-4646.1869","journal-title":"Journal of Mobile Multimedia"},{"key":"10098_CR14","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.neunet.2021.02.008","volume":"139","author":"S Gupta","year":"2021","unstructured":"Gupta, S., Patil, A. T., Purohit, M., Parmar, M., Patel, M., Patil, H. A., & Guido, R. C. (2021). Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments. Neural Networks, 139, 105\u2013117. https:\/\/doi.org\/10.1016\/j.neunet.2021.02.008","journal-title":"Neural Networks"},{"key":"10098_CR5","doi-asserted-by":"publisher","unstructured":"Hashan, A. M., Bredikhin, B., Melnikov, Alexander, Valerievich, Bachurin, & Matvey, Vladimirovich. (n.d.). HyperDysarthria-RusspeechData [dataset]. Kaggle. https:\/\/doi.org\/10.34740\/KAGGLE\/DS\/3415744","DOI":"10.34740\/KAGGLE\/DS\/3415744"},{"key":"10098_CR15","doi-asserted-by":"publisher","unstructured":"Hashan, A. M., Al-Saeedi Adnan Adhab, K., Islam, R. M. R. U., Avinash, K., & Dey, S. (2023). Automated human facial emotion recognition system using depthwise separable convolutional neural network. In 2023 IEEE international conference on industry 4.0, Artificial Intelligence, and communications technology (IAICT), (pp.113\u2013117). https:\/\/doi.org\/10.1109\/IAICT59002.2023.10205785","DOI":"10.1109\/IAICT59002.2023.10205785"},{"key":"10098_CR16","doi-asserted-by":"publisher","first-page":"115013","DOI":"10.1016\/j.eswa.2021.115013","volume":"178","author":"O Karaman","year":"2021","unstructured":"Karaman, O., \u00c7ak\u0131n, H., Alhudhaif, A., & Polat, K. (2021). Robust automated Parkinson disease detection based on voice signals with transfer learning. Expert Systems with Applications, 178, 115013. https:\/\/doi.org\/10.1016\/j.eswa.2021.115013","journal-title":"Expert Systems with Applications"},{"key":"10098_CR17","doi-asserted-by":"publisher","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. https:\/\/doi.org\/10.48550\/ARXIV.1412.6980","DOI":"10.48550\/ARXIV.1412.6980"},{"key":"10098_CR18","unstructured":"Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., & Inman, D. J. (2019). 1D convolutional neural networks andapplications: A survey (arXiv:1905.03554). arXiv. http:\/\/arxiv.org\/abs\/1905.03554"},{"issue":"2","key":"10098_CR19","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1001\/archneur.58.2.265","volume":"58","author":"KJ Kluin","year":"2001","unstructured":"Kluin, K. J., Gilman, S., Foster, N. L., Sima, A. A. F., D\u2019Amato, C. J., Bruch, L. A., Bluemlein, L., Little, R., & Johanns, J. (2001). Neuropathological correlates of dysarthria in progressive supranuclear palsy. Archives of Neurology, 58(2), 265. https:\/\/doi.org\/10.1001\/archneur.58.2.265","journal-title":"Archives of Neurology"},{"key":"10098_CR20","doi-asserted-by":"publisher","first-page":"96162","DOI":"10.1109\/ACCESS.2020.2995737","volume":"8","author":"A Lauraitis","year":"2020","unstructured":"Lauraitis, A., Maskeliunas, R., Damasevicius, R., & Krilavicius, T. (2020). Detection of speech impairments using Cepstrum, auditory spectrogram and wavelet time scattering domain features.  IEEE Access: Practical Innovations, Open Solutions, 8, 96162\u201396172. https:\/\/doi.org\/10.1109\/ACCESS.2020.2995737","journal-title":"Ieee Access: Practical Innovations, Open Solutions"},{"key":"10098_CR21","doi-asserted-by":"publisher","first-page":"107392","DOI":"10.1016\/j.patcog.2020.107392","volume":"105","author":"H Li","year":"2020","unstructured":"Li, H., & Wang, W. (2020). Reinterpreting CTC training as iterative fitting. Pattern Recognition, 105, 107392. https:\/\/doi.org\/10.1016\/j.patcog.2020.107392","journal-title":"Pattern Recognition"},{"issue":"16","key":"10098_CR22","doi-asserted-by":"publisher","first-page":"6317","DOI":"10.3390\/s22166317","volume":"22","author":"DJ Miller","year":"2022","unstructured":"Miller, D. J., Sargent, C., & Roach, G. D. (2022). A validation of six wearable devices for estimating sleep, heart rate and heart rate variability in healthy adults. Sensors (Basel, Switzerland), 22(16), 6317. https:\/\/doi.org\/10.3390\/s22166317","journal-title":"Sensors (Basel, Switzerland)"},{"key":"10098_CR23","doi-asserted-by":"publisher","unstructured":"Mitchell, C., Bowen, A., Tyson, S., Butterfint, Z., & Conroy, P. (2017). Interventions for dysarthria due to stroke and other adult-acquired, non-progressive brain injury. Cochrane Database of Systematic Reviews, 2017(1). https:\/\/doi.org\/10.1002\/14651858.CD002088.pub3","DOI":"10.1002\/14651858.CD002088.pub3"},{"issue":"7","key":"10098_CR24","doi-asserted-by":"publisher","first-page":"4375","DOI":"10.1016\/j.jksuci.2021.04.002","volume":"34","author":"K Nugroho","year":"2022","unstructured":"Nugroho, K., Noersasongko, E., Purwanto, M., & Setiadi, D. R. I. M. (2022). Enhanced Indonesian ethnic speakerrecognition using data augmentation deep neural network. Journal of King Saud University - Computer and Information Sciences, 34(7), 4375\u20134384. https:\/\/doi.org\/10.1016\/j.jksuci.2021.04.002","journal-title":"Journal of King Saud University - Computer and Information Sciences"},{"key":"10098_CR25","doi-asserted-by":"publisher","unstructured":"Pang, J., Wang, Z., Tang, J., Xiao, M., & Yin, N. (2023). SA-GDA: Spectral augmentation for graph domain adaptation. Proceedings of the 31st ACM international conference on multimedia, (pp. 309\u2013318). https:\/\/doi.org\/10.1145\/3581783.3612264","DOI":"10.1145\/3581783.3612264"},{"key":"10098_CR26","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., M\u00fcller, A., Nothman, J., Louppe, G., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, \u00c9. (2018). Scikit-learn: Machine learning in Python (arXiv:1201.0490). arXiv. http:\/\/arxiv.org\/abs\/1201.0490."},{"issue":"2","key":"10098_CR27","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1109\/JSTSP.2019.2908700","volume":"13","author":"H Purwins","year":"2019","unstructured":"Purwins, H., Li, B., Virtanen, T., Schluter, J., Chang, S. Y., & Sainath, T. (2019). Deep learning for audio signal processing. IEEE Journal of Selected Topics in Signal Processing, 13(2), 206\u2013219. https:\/\/doi.org\/10.1109\/JSTSP.2019.2908700","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"3","key":"10098_CR28","first-page":"12","volume":"2","author":"HK Rouzbahani","year":"2011","unstructured":"Rouzbahani, H. K., & Daliri, M. R. (2011). Diagnosis of Parkinson\u2019s disease in human using voice signals. Basic and Clinical Neuroscience, 2(3), 12\u201320.","journal-title":"Basic and Clinical Neuroscience"},{"key":"10098_CR29","doi-asserted-by":"publisher","unstructured":"Rueda, A., & Krishnan, S. (2019). Augmenting dysphonia voice using Fourier-based synchrosqueezing transform for a CNN classifier. In 2019 IEEE international conference on acoustics, speech and signal processing (ICASSP 2019), (pp. 6415\u20136419). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682391","DOI":"10.1109\/ICASSP.2019.8682391"},{"key":"10098_CR30","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/j.procs.2018.04.298","volume":"131","author":"G Shen","year":"2018","unstructured":"Shen, G., Tan, Q., Zhang, H., Zeng, P., & Xu, J. (2018). Deep learning with gated recurrent unit networks for financial sequence predictions. Procedia Computer Science, 131, 895\u2013903. https:\/\/doi.org\/10.1016\/j.procs.2018.04.298","journal-title":"Procedia Computer Science"},{"issue":"1","key":"10098_CR32","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.pneurobio.2006.11.009","volume":"81","author":"N Singh","year":"2007","unstructured":"Singh, N., Pillay, V., & Choonara, Y. E. (2007). Advances in the treatment of Parkinson\u2019s disease. Progress in Neurobiology, 81(1), 29\u201344. https:\/\/doi.org\/10.1016\/j.pneurobio.2006.11.009","journal-title":"Progress in Neurobiology"},{"key":"10098_CR31","doi-asserted-by":"publisher","unstructured":"Singh, G., Sharma, S., Kumar, V., Kaur, M., Baz, M., & Masud, M. (2021). Spoken language identification using deep learning. Computational Intelligence and Neuroscience, 2021, 1\u201312. https:\/\/doi.org\/10.1155\/2021\/5123671","DOI":"10.1155\/2021\/5123671"},{"key":"10098_CR33","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1109\/EUSIPCO.2015.7362616","volume":"1411","author":"Y Takashima","year":"2015","unstructured":"Takashima, Y., Nakashika, T., Takiguchi, T., & Ariki, Y. (2015). Feature extraction using pre-trained convolutive bottleneck nets for dysarthric speech recognition. 2015 23rd European signal processing conference (EUSIPCO), (pp. 1411, 1415). https:\/\/doi.org\/10.1109\/EUSIPCO.2015.7362616","journal-title":"2015 23rd European Signal Processing Conference (EUSIPCO)"},{"key":"10098_CR34","doi-asserted-by":"publisher","unstructured":"Tejaswi, S., & Umesh, S. (2017). DNN acoustic models for dysarthric speech. 2017 twenty-third national conference on communications (NCC), (pp. 1\u20134). https:\/\/doi.org\/10.1109\/NCC.2017.8077102","DOI":"10.1109\/NCC.2017.8077102"},{"key":"10098_CR35","doi-asserted-by":"publisher","unstructured":"Wang, P., Sun, R., Zhao, H., & Yu, K. (2013). A new word language model evaluation metric for character based languages. In M. Sun, M. Zhang, D. Lin, & H. Wang (Eds.), Chinese computational linguistics and natural language processing based on naturally annotated Big Data (Vol. 8202, pp. 315\u2013324). Springer. https:\/\/doi.org\/10.1007\/978-3-642-41491-6_29","DOI":"10.1007\/978-3-642-41491-6_29"},{"key":"10098_CR36","doi-asserted-by":"publisher","unstructured":"Yue, Z., Loweimi, E., Christensen, H., Barker, J., & Cvetkovic, Z. (2022). Dysarthric speech recognition from raw waveform with parametric CNNs. Interspeech 2022, 31-35, https:\/\/doi.org\/10.21437\/Interspeech.2022-163","DOI":"10.21437\/Interspeech.2022-163"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10098-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10098-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10098-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T15:15:33Z","timestamp":1715613333000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10098-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10098"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10098-5","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]},"assertion":[{"value":"9 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}