{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:19:01Z","timestamp":1749269941651,"version":"3.40.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"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":[[2025,5]]},"DOI":"10.1007\/s00034-024-02967-w","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T15:52:43Z","timestamp":1735660363000},"page":"3370-3387","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pathological Speech and Electroglottography Signals Analysis Using Invariance Scattering Network"],"prefix":"10.1007","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1402-4312","authenticated-orcid":false,"given":"Deepak","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Udit","family":"Satija","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Preetam","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"2967_CR1","doi-asserted-by":"crossref","unstructured":"Z.A. Aldoulah, M. Hafiz, R. Molyet, A novel fused multi-class deep learning approach for chronic wounds classification. Appl. Sci. 13(21) (2023)","DOI":"10.3390\/app132111630"},{"key":"2967_CR2","doi-asserted-by":"publisher","first-page":"46474","DOI":"10.1109\/ACCESS.2019.2905597","volume":"7","author":"M Alhussein","year":"2019","unstructured":"M. Alhussein, G. Muhammad, Automatic voice pathology monitoring using parallel deep models for smart healthcare. IEEE Access 7, 46474\u201346479 (2019)","journal-title":"IEEE Access"},{"issue":"16","key":"2967_CR3","doi-asserted-by":"publisher","first-page":"4114","DOI":"10.1109\/TSP.2014.2326991","volume":"62","author":"J Anden","year":"2014","unstructured":"J. Anden, S. Mallat, Deep scattering spectrum. IEEE Trans. Signal Process. 62(16), 4114\u20134128 (2014)","journal-title":"IEEE Trans. Signal Process."},{"key":"2967_CR4","doi-asserted-by":"crossref","unstructured":"P. Barche, K. Gurugubelli, A.K. Vuppala, Towards automatic assessment of voice disorders: a clinical approach, in Proceeding Interspeech 2020 (2020), pp. 2537\u20132541","DOI":"10.21437\/Interspeech.2020-2160"},{"issue":"8","key":"2967_CR5","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2012.230","volume":"35","author":"J Bruna","year":"2013","unstructured":"J. Bruna, S. Mallat, Invariant scattering convolution networks. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1872\u20131886 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"12","key":"2967_CR6","doi-asserted-by":"publisher","first-page":"3294","DOI":"10.1162\/NECO_a_00523","volume":"25","author":"L Chen","year":"2013","unstructured":"L. Chen, X. Mao, P. Wei, A. Compare, Speech emotional features extraction based on electroglottograph. Neural Comput. 25(12), 3294\u20133317 (2013)","journal-title":"Neural Comput."},{"issue":"12","key":"2967_CR7","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TBME.1984.325242","volume":"31","author":"DG Childers","year":"1984","unstructured":"D.G. Childers, J.N. Larar, Electroglottography for laryngeal function assessment and speech analysis. IEEE Trans. Biomed. Eng. 31(12), 807\u2013817 (1984)","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2967_CR8","doi-asserted-by":"crossref","unstructured":"H. Cordeiro, J. Fonseca, I. Guimar\u00e3es, C. Meneses, Voice pathologies identification speech signals, features and classifiers evaluation, in 2015 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA) (2015), pp. 81\u201386","DOI":"10.1109\/SPA.2015.7365138"},{"issue":"4","key":"2967_CR9","first-page":"667","volume":"15","author":"G Daza-Santacoloma","year":"2009","unstructured":"G. Daza-Santacoloma, J.D. Arias-Londo\u00f1o, J.I. Godino-Llorente, N. S\u00e1enz-Lech\u00f3n, V. Osma-Ru\u00edz, G. Castellanos-Dom\u00ednguez, Dynamic feature extraction: an application to voice pathology detection. Intell. Autom. Soft Comput. 15(4), 667\u2013682 (2009)","journal-title":"Intell. Autom. Soft Comput."},{"key":"2967_CR10","doi-asserted-by":"publisher","first-page":"1707","DOI":"10.1007\/s00034-022-02189-y","volume":"42","author":"S Deb","year":"2023","unstructured":"S. Deb, P. Warule, A. Nair, H. Sultan, R. Dash, J. Krajewski, Detection of common cold from speech signals using deep neural network. Circuits Syst. Signal Process. 42, 1707\u20131722 (2023)","journal-title":"Circuits Syst. Signal Process."},{"issue":"5","key":"2967_CR11","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1109\/TASL.2013.2244083","volume":"21","author":"L Deng","year":"2013","unstructured":"L. Deng, X. Li, Machine learning paradigms for speech recognition: an overview. IEEE Trans. Audio Speech Lang. Process. 21(5), 1060\u20131089 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2967_CR12","doi-asserted-by":"crossref","unstructured":"J. Driedger, M. M\u00fcller. A review of time-scale modification of music signals. Appl. Sci. 6(2) (2016)","DOI":"10.3390\/app6020057"},{"issue":"2","key":"2967_CR13","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2016","unstructured":"F. Eyben, K.R. Scherer, B.W. Schuller et al., The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2), 190\u2013202 (2016)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"2967_CR14","doi-asserted-by":"crossref","unstructured":"F. Eyben, M. W\u00f6llmer, B. Schuller. Opensmile: the Munich versatile and fast open-source audio feature extractor, in Proceedings of the 18th ACM International Conference on Multimedia (New York, 2010), pp. 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"key":"2967_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.101615","volume":"55","author":"ES Fonseca","year":"2020","unstructured":"E.S. Fonseca, R.C. Guido, S.B. Junior, H. Dezani, R.R. Gati, D.C. Mosconi Pereira, Acoustic investigation of speech pathologies based on the discriminative paraconsistent machine (DPM). Biomed. Signal Process. Control 55, 101615 (2020)","journal-title":"Biomed. Signal Process. Control"},{"key":"2967_CR16","doi-asserted-by":"crossref","unstructured":"P. Harar, J.B. Alonso-Hernandezy, J. Mekyska, Z. Galaz, R. Burget, Z. Smekal, Voice pathology detection using deep learning: a preliminary study, in 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI) (2017), pp. 1\u20134","DOI":"10.1109\/IWOBI.2017.7985525"},{"key":"2967_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.mex.2022.101739","volume":"9","author":"ME Hernandez","year":"2022","unstructured":"M.E. Hernandez, L. Ziegelman, T. Kosuri, H. Hakim, L. Zhao, K.A. Mills, J.R. Bra\u0161i\u0107, Classification of extremity movements by visual observation of signals and their transforms. MethodsX 9, 101739 (2022)","journal-title":"MethodsX"},{"issue":"2","key":"2967_CR18","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/JSTSP.2019.2957988","volume":"14","author":"SR Kadiri","year":"2020","unstructured":"S.R. Kadiri, P. Alku, Analysis and detection of pathological voice using glottal source features. IEEE J. Sel. Signal Process. 14(2), 367\u2013379 (2020)","journal-title":"IEEE J. Sel. Signal Process."},{"issue":"15","key":"2967_CR19","doi-asserted-by":"publisher","first-page":"17017","DOI":"10.1109\/JSEN.2021.3080135","volume":"21","author":"SK Khare","year":"2021","unstructured":"S.K. Khare, V. Bajaj, U.R. Acharya, PDCNNet: An automatic framework for the detection of Parkinson\u2019s disease using EEG signals. IEEE Sens. J. 21(15), 17017\u201317024 (2021)","journal-title":"IEEE Sens. J."},{"key":"2967_CR20","doi-asserted-by":"crossref","unstructured":"D. Kumar, U. Satija, P. Kumar, Automated classification of pathological speech signals, in 2022 IEEE 19th India Council International Conference (INDICON) (2022), pp. 1\u20135","DOI":"10.1109\/INDICON56171.2022.10040139"},{"key":"2967_CR21","doi-asserted-by":"crossref","unstructured":"D. Kumar, U. Satija, P. Kumar, Analysis and classification of electroglottography signals for the detection of speech disorders, in 2023 National Conference on Communications (NCC) (2023), pp 1\u20136","DOI":"10.1109\/NCC56989.2023.10067972"},{"key":"2967_CR22","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1007\/s00034-017-0582-x","volume":"37","author":"GJ Lal","year":"2018","unstructured":"G.J. Lal, E.A. Gopalakrishnan, D. Govind, Accurate estimation of glottal closure instants and glottal opening instants from electroglottographic signal using variational mode decomposition. Circuits Syst. Signal Process. 37, 810\u2013830 (2018)","journal-title":"Circuits Syst. Signal Process."},{"key":"2967_CR23","doi-asserted-by":"crossref","unstructured":"Z. Liu, G. Yao, Q. Zhang, J. Zhang, X. Zeng, Wavelet scattering transform for ECG beat classification. Comput. Math. Methods Med. (2020)","DOI":"10.1155\/2020\/3215681"},{"issue":"10","key":"2967_CR24","doi-asserted-by":"publisher","first-page":"1331","DOI":"10.1002\/cpa.21413","volume":"65","author":"S Mallat","year":"2012","unstructured":"S. Mallat, Group invariant scattering. Commun. Pure Appl. Math. 65(10), 1331\u20131398 (2012)","journal-title":"Commun. Pure Appl. Math."},{"key":"2967_CR25","doi-asserted-by":"publisher","first-page":"89198","DOI":"10.1109\/ACCESS.2021.3090317","volume":"9","author":"G Muhammad","year":"2021","unstructured":"G. Muhammad, M. Alhussein, Convergence of artificial intelligence and internet of things in smart healthcare: a case study of voice pathology detection. IEEE Access 9, 89198\u201389209 (2021)","journal-title":"IEEE Access"},{"key":"2967_CR26","doi-asserted-by":"publisher","first-page":"1925","DOI":"10.1109\/TASLP.2021.3078364","volume":"29","author":"N Narendra","year":"2021","unstructured":"N. Narendra, B. Schuller, P. Alku, The detection of Parkinson\u2019s disease from speech using voice source information. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 1925\u20131936 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"6","key":"2967_CR27","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1109\/JBHI.2015.2467375","volume":"19","author":"JR Orozco-Arroyave","year":"2015","unstructured":"J.R. Orozco-Arroyave, E.A. Belalcazar-Bolanos, J.D. Arias-Londo\u00f1o, J.F. Vargas-Bonilla, S. Skodda, J. Rusz, K. Daqrouq, F. H\u00f6nig, E. N\u00f6th, Characterization methods for the detection of multiple voice disorders: neurological, functional, and laryngeal diseases. IEEE J. Biomed. Health Inform. 19(6), 1820\u20131828 (2015)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2967_CR28","unstructured":"M. Putzer, W.J. Barry, Saarbrucken voice database. Institute of Phonetics, University of Saarland (2023). http:\/\/www.stimmdatenbank.coli.uni-saarland.de\/"},{"key":"2967_CR29","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.1007\/s00034-017-0654-y","volume":"37","author":"GA Rachel","year":"2018","unstructured":"G.A. Rachel, N. Sripriya, P. Vijayalakshmi, T. Nagarajan, Significance of differenced egg signal as a spectrum in phase difference computation for the estimation of glottal closure instants. Circuits Syst. Signal Process. 37, 2074\u20132097 (2018)","journal-title":"Circuits Syst. Signal Process."},{"key":"2967_CR30","doi-asserted-by":"publisher","first-page":"15273","DOI":"10.1109\/ACCESS.2020.2967224","volume":"8","author":"MK Reddy","year":"2020","unstructured":"M.K. Reddy, P. Alku, K.S. Rao, Detection of specific language impairment in children using glottal source features. IEEE Access 8, 15273\u201315279 (2020)","journal-title":"IEEE Access"},{"key":"2967_CR31","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1109\/LSP.2022.3199669","volume":"29","author":"MK Reddy","year":"2022","unstructured":"M.K. Reddy, Y.M. Keerthana, P. Alku, End-to-end pathological speech detection using wavelet scattering network. IEEE Signal Process. Lett. 29, 1863\u20131867 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"2967_CR32","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.1007\/s00034-014-9927-x","volume":"34","author":"P Saidi","year":"2015","unstructured":"P. Saidi, F. Almasganj, Voice disorder signal classification using m-band wavelets and support vector machine. Circuits Syst. Signal Process. 34, 2727\u20132738 (2015)","journal-title":"Circuits Syst. Signal Process."},{"issue":"3","key":"2967_CR33","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","volume":"24","author":"J Salamon","year":"2017","unstructured":"J. Salamon, J.P. Bello, Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279\u2013283 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"2967_CR34","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1016\/j.bbe.2020.01.003","volume":"1","author":"G Solana-Lavalle","year":"2020","unstructured":"G. Solana-Lavalle, J.-C. Gal\u00e1n-Hern\u00e1ndez, R. Rosas-Romero, Automatic Parkinson disease detection at early stages as a pre-diagnosis tool by using classifiers and a small set of vocal features. Biocybern. Biomed. Eng. 1, 505\u2013516 (2020)","journal-title":"Biocybern. Biomed. Eng."},{"key":"2967_CR35","doi-asserted-by":"publisher","first-page":"16246","DOI":"10.1109\/ACCESS.2018.2816338","volume":"6","author":"L Verde","year":"2018","unstructured":"L. Verde, G.D. Pietro, G. Sannino, Voice disorder identification by using machine learning techniques. IEEE Access 6, 16246\u201316255 (2018)","journal-title":"IEEE Access"},{"key":"2967_CR36","doi-asserted-by":"crossref","unstructured":"H. Wu, J. Soraghan, A. Lowit, G. Di-Caterina, A deep learning method for pathological voice detection using convolutional deep belief networks, in Interspeech 2018 (2018), pp. 446\u2013450","DOI":"10.21437\/Interspeech.2018-1351"},{"issue":"2","key":"2967_CR37","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.57185\/joss.v3i2.285","volume":"3","author":"A Yudhasmara","year":"2024","unstructured":"A. Yudhasmara, A.K. Adani, I.N. Dewi, W. Judarwanto, S. Yudhasmara, Picky eating in children: oral motor disorder and delayed speech as risk factor. J. Soc. Sci. (JoSS) 3(2), 1285\u20131293 (2024)","journal-title":"J. Soc. Sci. (JoSS)"},{"issue":"4","key":"2967_CR38","doi-asserted-by":"publisher","first-page":"2614","DOI":"10.1121\/1.4964509","volume":"140","author":"Z Zhang","year":"2016","unstructured":"Z. Zhang, Mechanics of human voice production and control. J. Acoust. Soc. Am. 140(4), 2614\u20132635 (2016)","journal-title":"J. Acoust. Soc. Am."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02967-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-024-02967-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-024-02967-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,19]],"date-time":"2025-04-19T02:49:58Z","timestamp":1745030998000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-024-02967-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"references-count":38,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2967"],"URL":"https:\/\/doi.org\/10.1007\/s00034-024-02967-w","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2024,12,31]]},"assertion":[{"value":"27 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 December 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}