{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:18:14Z","timestamp":1779333494739,"version":"3.51.4"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"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":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1007\/s00034-024-02611-7","type":"journal-article","created":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T07:03:51Z","timestamp":1708585431000},"page":"3261-3278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Variable STFT Layered CNN Model for Automated Dysarthria Detection and Severity Assessment Using Raw Speech"],"prefix":"10.1007","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8064-0440","authenticated-orcid":false,"given":"Kodali","family":"Radha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0524-8251","authenticated-orcid":false,"given":"Mohan","family":"Bansal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-4011","authenticated-orcid":false,"given":"Venkata Rao","family":"Dhulipalla","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"issue":"2","key":"2611_CR1","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1109\/JSTSP.2020.2967652","volume":"14","author":"C Bhat","year":"2020","unstructured":"C. Bhat, H. Strik, Automatic assessment of sentence-level dysarthria intelligibility using BLSTM. IEEE J. Select. Top. Signal Process. 14(2), 322\u2013330 (2020)","journal-title":"IEEE J. Select. Top. Signal Process."},{"key":"2611_CR2","doi-asserted-by":"crossref","unstructured":"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\u20135074","DOI":"10.1109\/ICASSP.2017.7953122"},{"issue":"3","key":"2611_CR3","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1111\/1460-6984.12715","volume":"57","author":"M Carl","year":"2022","unstructured":"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\u2013679 (2022)","journal-title":"Int. J. Lang. Commun. Disord."},{"issue":"2","key":"2611_CR4","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1109\/JSTSP.2019.2949912","volume":"14","author":"H Chandrashekar","year":"2019","unstructured":"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\u2013399 (2019)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"12","key":"2611_CR5","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TNSRE.2020.3035392","volume":"28","author":"H Chandrashekar","year":"2020","unstructured":"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\u20132889 (2020)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2611_CR6","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1016\/B978-0-444-52901-5.00022-8","volume":"110","author":"P Enderby","year":"2013","unstructured":"P. Enderby, Disorders of communication: dysarthria. Handb. Clin. Neurol. 110, 273\u2013281 (2013)","journal-title":"Handb. Clin. Neurol."},{"key":"2611_CR7","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/LSP.2021.3050362","volume":"28","author":"J Fritsch","year":"2021","unstructured":"J. Fritsch, M. Magimai-Doss, Utterance verification-based dysarthric speech intelligibility assessment using phonetic posterior features. IEEE Signal Process. Lett. 28, 224\u2013228 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"2611_CR8","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.neucom.2021.05.065","volume":"456","author":"A Gallardo-Antol\u00edn","year":"2021","unstructured":"A. Gallardo-Antol\u00edn, J.M. Montero, On combining acoustic and modulation spectrograms in an attention LSTM-based system for speech intelligibility level classification. Neurocomputing 456, 49\u201360 (2021)","journal-title":"Neurocomputing"},{"key":"2611_CR9","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.neunet.2021.02.008","volume":"139","author":"S Gupta","year":"2021","unstructured":"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\u2013117 (2021)","journal-title":"Neural Netw."},{"issue":"19","key":"2611_CR10","doi-asserted-by":"publisher","first-page":"6999","DOI":"10.3390\/app10196999","volume":"10","author":"A Hernandez","year":"2020","unstructured":"A. Hernandez, S. Kim, M. Chung, Prosody-based measures for automatic severity assessment of dysarthric speech. Appl. Sci. 10(19), 6999 (2020)","journal-title":"Appl. Sci."},{"issue":"7","key":"2611_CR11","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1016\/j.ymssp.2005.09.012","volume":"20","author":"AK Jardine","year":"2006","unstructured":"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\u20131510 (2006)","journal-title":"Mech. Syst. Signal Process."},{"key":"2611_CR12","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TNSRE.2022.3169814","volume":"30","author":"AA Joshy","year":"2022","unstructured":"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\u20131157 (2022)","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"2611_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.bspc.2023.104606","volume":"82","author":"AA Joshy","year":"2023","unstructured":"A.A. Joshy, R. Rajan, Dysarthria severity assessment using squeeze-and-excitation networks. Biomed. Signal Process. Control 82, 1\u201313 (2023)","journal-title":"Biomed. Signal Process. Control"},{"key":"2611_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2022.12.004","volume":"147","author":"AA Joshy","year":"2023","unstructured":"A.A. Joshy, R. Rajan, Dysarthria severity classification using multi-head attention and multi-task learning. Speech Commun. 147, 1\u201311 (2023)","journal-title":"Speech Commun."},{"key":"2611_CR15","doi-asserted-by":"crossref","unstructured":"A. Kachhi, A. Therattil, P. Gupta et\u00a0al, Continuous wavelet transform for severity-level classification of dysarthria, in International Conference on Speech and Computer (Springer, 2022), pp. 312\u2013324","DOI":"10.1007\/978-3-031-20980-2_27"},{"key":"2611_CR16","doi-asserted-by":"crossref","unstructured":"H. Kim, M. Hasegawa-Johnson, A. Perlman et\u00a0al, Dysarthric speech database for universal access research, in Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH, 2008), pp. 1741\u20131744","DOI":"10.21437\/Interspeech.2008-480"},{"key":"2611_CR17","doi-asserted-by":"crossref","unstructured":"D. Korzekwa, R. Barra-Chicote, B. Kostek et\u00a0al, Interpretable deep learning model for the detection and reconstruction of dysarthric speech. arXiv:1907.04743 (2019)","DOI":"10.21437\/Interspeech.2019-1206"},{"key":"2611_CR18","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1109\/RBME.2020.3006860","volume":"14","author":"S Latif","year":"2020","unstructured":"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\u2013356 (2020)","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"2611_CR19","doi-asserted-by":"crossref","unstructured":"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\u20136462","DOI":"10.1109\/ICASSP39728.2021.9413625"},{"key":"2611_CR20","unstructured":"V. Mendoza\u00a0Ramos, The added value of speech technology in clinical care of patients with dysarthria. Ph.D. thesis, University of Antwerp (2022)"},{"key":"2611_CR21","doi-asserted-by":"crossref","unstructured":"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\u20135835","DOI":"10.1109\/ICASSP.2019.8682324"},{"key":"2611_CR22","doi-asserted-by":"publisher","first-page":"67745","DOI":"10.1109\/ACCESS.2020.2986171","volume":"8","author":"N Narendra","year":"2020","unstructured":"N. Narendra, P. Alku, Glottal source information for pathological voice detection. IEEE Access 8, 67745\u201367755 (2020)","journal-title":"IEEE Access"},{"key":"2611_CR23","doi-asserted-by":"publisher","unstructured":"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\u20137. https:\/\/doi.org\/10.1109\/ICCCNT56998.2023.10307923","DOI":"10.1109\/ICCCNT56998.2023.10307923"},{"issue":"10","key":"2611_CR24","doi-asserted-by":"publisher","first-page":"6228","DOI":"10.1007\/s00034-023-02399-y","volume":"42","author":"K Radha","year":"2023","unstructured":"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\u20136252 (2023)","journal-title":"Circuits Syst. Signal Process."},{"issue":"3","key":"2611_CR25","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1007\/s10772-023-10039-8","volume":"26","author":"K Radha","year":"2023","unstructured":"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\u2013650 (2023)","journal-title":"Int. J. Speech Technol."},{"issue":"107","key":"2611_CR26","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1016\/j.engappai.2023.107661","volume":"131","author":"K Radha","year":"2024","unstructured":"K. Radha, M. Bansal, R.B. Pachori, Speech and speaker recognition using raw waveform modeling for adult and children\u2019s speech: a comprehensive review. Eng. Appl. Artif. Intell. 131(107), 661 (2024). https:\/\/doi.org\/10.1016\/j.engappai.2023.107661","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"119","key":"2611_CR27","first-page":"293","volume":"215","author":"S Reza","year":"2023","unstructured":"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)","journal-title":"Expert Syst. Appl."},{"key":"2611_CR28","unstructured":"P. Roussel, Analysis of cortical activity for the development of brain-computer interfaces for speech. Ph.d. thesis, Universit\u00e9 Grenoble Alpes (2021)"},{"key":"2611_CR29","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","volume":"46","author":"F Rudzicz","year":"2012","unstructured":"F. Rudzicz, A.K. Namasivayam, T. Wolff, The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang. Resour. Eval. 46, 523\u2013541 (2012)","journal-title":"Lang. Resour. Eval."},{"key":"2611_CR30","doi-asserted-by":"crossref","unstructured":"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)","DOI":"10.1109\/ICASSP49357.2023.10095981"},{"key":"2611_CR31","doi-asserted-by":"publisher","unstructured":"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\u20136. https:\/\/doi.org\/10.1109\/ELEXCOM58812.2023.10370116","DOI":"10.1109\/ELEXCOM58812.2023.10370116"},{"key":"2611_CR32","doi-asserted-by":"publisher","unstructured":"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\u20137. https:\/\/doi.org\/10.1109\/ICCCNT56998.2023.10308048","DOI":"10.1109\/ICCCNT56998.2023.10308048"},{"key":"2611_CR33","doi-asserted-by":"crossref","unstructured":"B. Suhas, D. Patel, N.R. Koluguri et\u00a0al, 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\u20134568","DOI":"10.21437\/Interspeech.2019-1285"},{"key":"2611_CR34","doi-asserted-by":"crossref","unstructured":"B. Suhas, J. Mallela, A. Illa et\u00a0al, Speech task based automatic classification of als and parkinson\u2019s disease and their severity using log mel spectrograms, in 2020 International Conference on Signal Processing and Communications (SPCOM) (IEEE, 2020), pp. 1\u20135","DOI":"10.1109\/SPCOM50965.2020.9179503"},{"issue":"4","key":"2611_CR35","first-page":"791","volume":"9","author":"N Tavabi","year":"2022","unstructured":"N. Tavabi, D. St\u00fcck, A. Signorini et al., Cognitive digital biomarkers from automated transcription of spoken language. J. Prevent. Alzheimer\u2019s Dis. 9(4), 791\u2013800 (2022)","journal-title":"J. Prevent. Alzheimer\u2019s Dis."},{"issue":"3","key":"2611_CR36","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1007\/s00415-022-11464-6","volume":"270","author":"MJ Vansteensel","year":"2023","unstructured":"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\u20131336 (2023)","journal-title":"J. Neurol."},{"key":"2611_CR37","unstructured":"P.W. Wong, N. Moayeri, C. Herley, Optimum pre-and post-filters for robust scalar quantization, in Proceedings of Data Compression Conference-DCC\u201996 (IEEE, 2022), pp. 240\u2013249"},{"issue":"5","key":"2611_CR38","doi-asserted-by":"publisher","first-page":"S46","DOI":"10.1044\/jshr.3905.s46","volume":"39","author":"KM Yorkston","year":"1996","unstructured":"K.M. Yorkston, Treatment efficacy: dysarthria. J. Speech Lang. Hear. Res. 39(5), S46\u2013S57 (1996)","journal-title":"J. Speech Lang. Hear. Res."},{"key":"2611_CR39","doi-asserted-by":"crossref","unstructured":"Z. Yue, E. Loweimi, H. Christensen, et\u00a0al., Dysarthric speech recognition from raw waveform with parametric CNNs, in Proceedings of INTERSPEECH 2022. ISCA-INST SPEECH COMMUNICATION ASSOC (2022)","DOI":"10.21437\/Interspeech.2022-163"}],"updated-by":[{"DOI":"10.1007\/s00034-024-02728-9","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000}}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02611-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-024-02611-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02611-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T06:12:44Z","timestamp":1731391964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-024-02611-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":39,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["2611"],"URL":"https:\/\/doi.org\/10.1007\/s00034-024-02611-7","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s00034-024-02728-9","asserted-by":"object"}]},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]},"assertion":[{"value":"19 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2024","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s00034-024-02728-9","URL":"https:\/\/doi.org\/10.1007\/s00034-024-02728-9","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}