{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:23:40Z","timestamp":1772119420188,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T00:00:00Z","timestamp":1699401600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T00:00:00Z","timestamp":1699401600000},"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":["Soft Comput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00500-023-09302-6","type":"journal-article","created":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T12:02:09Z","timestamp":1699444929000},"page":"5683-5698","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Comparative analysis of deep learning models for dysarthric speech detection"],"prefix":"10.1007","volume":"28","author":[{"given":"P.","family":"Shanmugapriya","sequence":"first","affiliation":[]},{"given":"V.","family":"Mohan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,8]]},"reference":[{"key":"9302_CR1","unstructured":"Amlu AJ, Rajeev R (2020) Automated dysarthria severity classification using deep learning frameworks. In: EUSIPCO 2020, pp 116\u2013120"},{"issue":"3","key":"9302_CR2","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1159\/000497178","volume":"72","author":"SD Barreto","year":"2020","unstructured":"Barreto SD, Ortiz KZ (2020) Speech intelligibility in dysarthrias: influence of utterance length. Folia Phoniatr Logop 72(3):202\u2013210","journal-title":"Folia Phoniatr Logop"},{"key":"9302_CR3","doi-asserted-by":"publisher","first-page":"18183","DOI":"10.1109\/ACCESS.2021.3053335","volume":"9","author":"A-Q Bassam Ali","year":"2021","unstructured":"Bassam Ali A-Q, Mumtaz BM (2021) Classification of dysarthric speech according to the severity of impairment: an analysis of acoustic features. IEEE Access 9:18183\u201318194","journal-title":"IEEE Access"},{"key":"9302_CR4","doi-asserted-by":"publisher","DOI":"10.1159\/000511042","author":"I Calvo","year":"2020","unstructured":"Calvo I, Tropea P, Vigano M, Scialla M, Cavalcante AB, Grajzer M, Gilardone M, Corbo M (2020) Evaluation of an automatic speech recognition platform for dysarthric speech. Folia Phoniatr Logop. https:\/\/doi.org\/10.1159\/000511042","journal-title":"Folia Phoniatr Logop"},{"issue":"2","key":"9302_CR5","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/JSTSP.2019.2949912","volume":"14","author":"HM Chandrashekar","year":"2020","unstructured":"Chandrashekar HM, Karjigi V, Sreedevi N (2020) Spectro-temporal representation of speech for intelligibility assessment of dysarthria. IEEE J Sel Top Signal Process 14(2):390\u2013399","journal-title":"IEEE J Sel Top Signal Process"},{"issue":"1","key":"9302_CR6","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1044\/2016_JSLHR-S-15-0291","volume":"60","author":"KP Connaghan","year":"2017","unstructured":"Connaghan KP, Patel R (2017) The impact of contrastive stress on vowel acoustics and intelligibility in dysarthria. J Speech Lang Hear Res 60(1):38\u201350","journal-title":"J Speech Lang Hear Res"},{"key":"9302_CR7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683314","author":"K Gurugubelli","year":"2019","unstructured":"Gurugubelli K, Vuppala AK (2019) Perceptually enhanced single frequency filtering for dysarthric speech detection and intelligibility assessment. Int Conf Acoust Speech Signal Process. https:\/\/doi.org\/10.1109\/ICASSP.2019.8683314","journal-title":"Int Conf Acoust Speech Signal Process"},{"issue":"4","key":"9302_CR8","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1097\/TLD.0000000000000137","volume":"37","author":"EK Hanson","year":"2017","unstructured":"Hanson EK, Fager SK (2017) Communication supports for people with motor speech disorders. Topics Lang Disorders 37(4):375\u2013388","journal-title":"Topics Lang Disorders"},{"key":"9302_CR9","doi-asserted-by":"publisher","DOI":"10.1049\/cp.2017.0360","author":"TB Ijitona","year":"2017","unstructured":"Ijitona TB, Soraghan JJ, Lowit A, Di-Caterina G, Yue H (2017) Automatic detection of speech disorder in dysarthria using extended speech feature extraction and neural networks classification. IET Int Conf Intell Signal Process. https:\/\/doi.org\/10.1049\/cp.2017.0360","journal-title":"IET Int Conf Intell Signal Process"},{"key":"9302_CR108","unstructured":"Keskar NS, Socher R (2017) Improving generalization performance by switching from adam to sgd. arxiv: https:\/\/arxiv.org\/abs\/1712.07628"},{"key":"9302_CR10","unstructured":"Korzekwa D, Roberto B-C, Bozena K, Thomas D, Mateusz L (2023) Interpretable deep learning model for the detection and reconstruction of dysarthric speech. Electrical Engineering and Systems Science, Audio and Speech Processing, arxiv: https:\/\/arxiv.org\/abs\/1907.04743"},{"key":"9302_CR106","doi-asserted-by":"crossref","unstructured":"Kronland-Martinet R, Morlet J, Grossmann A (1987) Analysis of sound patterns through wavelet transforms. Int J Pattern Recog Artif Intell 1(2):273\u2013302","DOI":"10.1142\/S0218001487000205"},{"key":"9302_CR105","doi-asserted-by":"crossref","unstructured":"Kronland-Martinet R (1988) The wavelet transform for analysis, synthesis, and processing of speech and music sounds. Computer Music J 12(4):11\u201320","DOI":"10.2307\/3680149"},{"key":"9302_CR11","unstructured":"Narendra NP, Alku P (2018) Dysarthric speech classification using glottal features computed from non-words, words and sentences. In: Interspeech"},{"key":"9302_CR100","doi-asserted-by":"publisher","unstructured":"Paja MS, Falk TH (2012) Automated dysarthria severity classification for improved objective intelligibility assessment of spastic dysarthric speech. Proceedings of interspeech, pp 62\u201365. https:\/\/doi.org\/10.21437\/Interspeech.2012-26","DOI":"10.21437\/Interspeech.2012-26"},{"key":"9302_CR107","unstructured":"Ramezani-Kebrya A, Khisti A, Liang B (2021) On the generalization of stochastic gradient descent with momentum. arxiv: https:\/\/arxiv.org\/abs\/2102.13653"},{"key":"9302_CR12","unstructured":"Rughani M, Shivakrishna D (2015) Hybridized feature extraction and acoustic modelling approach for dysarthric speech recognition. arxiv: https:\/\/arxiv.org\/abs\/1506.02170"},{"issue":"1","key":"9302_CR13","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.icte.2021.07.004","volume":"8","author":"SM Sekhar","year":"2022","unstructured":"Sekhar SM, Kashyap G, Bhansali A, Singh K (2022) Dysarthric-speech detection using transfer learning with convolutional neural networks. ICT Express 8(1):61\u201364","journal-title":"ICT Express"},{"key":"9302_CR14","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/TNSRE.2021.3076778","volume":"29","author":"SR Shahamiri","year":"2021","unstructured":"Shahamiri SR (2021) Speech vision: an end-to-end deep learning-based dysarthric automatic speech recognition system. IEEE Trans Neural Syst Rehabil Eng 29:852\u2013861","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"9302_CR15","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0169-5","author":"MY Sidi","year":"2020","unstructured":"Sidi MY, Selouani SA, Zaidi BF, Bouchair A (2020) Improving dysarthric speech recognition using empirical mode decomposition and convolutional neural network. EURASIP J Audio Speech Music Process. https:\/\/doi.org\/10.1186\/s13636-019-0169-5","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"9302_CR110","unstructured":"Smith SL, Kindermans PJ, Ying C, Le QV (2017) Don\u2019t decay the learning rate, increase the batch size. arxiv: https:\/\/arxiv.org\/abs\/1711.00489"},{"key":"9302_CR16","doi-asserted-by":"crossref","unstructured":"Souissi N Cherif A (2015) Dimensionality reduction for voice disorders identification system based on mel frequency cepstral coefficients and support vector Machine. In: 7th International Conference on Modelling, Identification and Control (ICMIC), pp 1\u20136","DOI":"10.1109\/ICMIC.2015.7409479"},{"key":"9302_CR17","doi-asserted-by":"crossref","unstructured":"Wisesty UN, Adiwijaya, Astuti W (2015) Feature extraction analysis on Indonesian speech recognition system. In: 3rd International Conference on Information and Communication Technology (ICoICT 2015), pp 54\u201358","DOI":"10.1109\/ICoICT.2015.7231396"},{"key":"9302_CR101","doi-asserted-by":"publisher","unstructured":"Xiong F, Barker J, Yue Z, Christensen H (2020) Source domain data selection for improved transfer learning targeting dysarthric speech recognition. In: ICASSP 2020 - 2020 IEEE international conference on acoustics, speech and signal processing (ICASSP), Barcelona, Spain, pp 7424\u20137428.\nhttps:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054694","DOI":"10.1109\/ICASSP40776.2020.9054694"},{"key":"9302_CR18","doi-asserted-by":"publisher","first-page":"935","DOI":"10.3390\/s19040935","volume":"19","author":"B Yeong-Hyeon","year":"2019","unstructured":"Yeong-Hyeon B, Sung-Bum P, Keun-Chang K (2019) Intelligent deep models based on scalograms of electrocardiogram signals for biometrics. Sensors 19:935","journal-title":"Sensors"},{"key":"9302_CR103","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. In: Proceedings of interspeech, pp 31\u201335. https:\/\/doi.org\/10.21437\/Interspeech.2022-163","DOI":"10.21437\/Interspeech.2022-163"},{"key":"9302_CR102","doi-asserted-by":"publisher","unstructured":"Zaidi BF, Selouani SA, Boudraa M et al (2021) Deep neural network architectures for dysarthric speech analysis and recognition. Neural Comput Appl 33:9089\u20139108. https:\/\/doi.org\/10.1007\/s00521-020-05672-2","DOI":"10.1007\/s00521-020-05672-2"},{"key":"9302_CR109","unstructured":"Zhou P, Feng J, Ma C, Xiong C, Hoi S (2020) Towards theoretically understanding why SGD generalizes better than adam in deep learning. arxiv: https:\/\/arxiv.org\/abs\/2010.05627"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-09302-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-023-09302-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-09302-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T09:22:28Z","timestamp":1709198548000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-023-09302-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,8]]},"references-count":28,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["9302"],"URL":"https:\/\/doi.org\/10.1007\/s00500-023-09302-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-1916239\/v1","asserted-by":"object"}]},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,8]]},"assertion":[{"value":"24 September 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2023","order":2,"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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"None.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}