{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:57:44Z","timestamp":1742972264290,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031779602"},{"type":"electronic","value":"9783031779619"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-77961-9_26","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T13:54:35Z","timestamp":1732197275000},"page":"352-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Binary and\u00a0Multiclass Classification of\u00a0Dysphonia Using Whisper Encoder and\u00a0One-Dimensional Convolutional Neural Network"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6449-7501","authenticated-orcid":false,"given":"Dosti","family":"Aziz","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7361-4260","authenticated-orcid":false,"given":"D\u00e1vid","family":"Sztah\u00f3","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"26_CR1","doi-asserted-by":"publisher","unstructured":"Amami, R., Amami, R., Trabelsi, C., Mabrouk, S.H., Khalil, H.A.: A Robust Voice Pathology Detection System Based on the Combined BiLSTM\u2013CNN Architecture. 1. 29(2), 202\u2013210 (2023). https:\/\/doi.org\/10.13164\/mendel.2023.2.202","DOI":"10.13164\/mendel.2023.2.202"},{"key":"26_CR2","doi-asserted-by":"publisher","unstructured":"Angelillo, I.F., Di Maio, G., Costa, G., Angelillo, I.F., Barillari U.: Prevalence of occupational voice disorders in teachers. J. Prev. Med. Hyg. 50(1), (2009). https:\/\/doi.org\/10.15167\/2421-4248\/jpmh2009.50.1.152","DOI":"10.15167\/2421-4248\/jpmh2009.50.1.152"},{"key":"26_CR3","unstructured":"Aronson, A.E.: Clinical Voice Disorders: An Interdisciplinary Approach. Thieme (1990)"},{"key":"26_CR4","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/JTEHM.2023.3340345","volume":"12","author":"D Aziz","year":"2023","unstructured":"Aziz, D., David, S.: Multitask and transfer learning approach for joint classification and severity estimation of dysphonia. IEEE J. Transl. Eng. Health Med. 12, 233\u2013244 (2023). https:\/\/doi.org\/10.1109\/JTEHM.2023.3340345","journal-title":"IEEE J. Transl. Eng. Health Med."},{"key":"26_CR5","doi-asserted-by":"publisher","unstructured":"Aziz, D., Sztah\u00f3, D.: Dysphonia detection using a fully convolutional neural network adapted to dynamic speech lengths. In: 2nd Workshop on Intelligent Infocommunication Networks, Systems and Services (WI2NS2) (2024). https:\/\/doi.org\/10.3311\/WINS2024-003","DOI":"10.3311\/WINS2024-003"},{"issue":"2","key":"26_CR6","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1111\/1460-6984.12783","volume":"58","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Zhu, P., Qiu, W., Guo, J., Li, Y.: Deep learning in automatic detection of dysphonia: Comparing acoustic features and developing a generalizable framework. Int. J. Lang. Commun. Disord. 58(2), 279\u2013294 (2023). https:\/\/doi.org\/10.1111\/1460-6984.12783","journal-title":"Int. J. Lang. Commun. Disord."},{"key":"26_CR7","unstructured":"Crevier-Buchman, L., Ch, T., Sauvignet, A., Brihaye-Arpin, S., Monfrais-Pfauwadel, M.C.: Diagnosis of non-organic dysphonia in adult. Revue de Laryngologie-Otologie-Rhinologie 126(5), 353\u2013360 (2005)"},{"issue":"10","key":"26_CR8","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.3390\/app8101927","volume":"8","author":"Z Dankovi\u010dov\u00e1","year":"2018","unstructured":"Dankovi\u010dov\u00e1, Z., Sov\u00e1k, D., Drot\u00e1r, P., Vokorokos, L.: Machine learning approach to dysphonia detection. Appl. Sci. 8(10), 1927 (2018). https:\/\/doi.org\/10.3390\/app8101927","journal-title":"Appl. Sci."},{"issue":"11","key":"26_CR9","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.1134\/S1064226914110059","volume":"59","author":"IMM El Emary","year":"2014","unstructured":"El Emary, I.M.M., Fezari, M., Amara, F.: Towards developing a voice pathologies detection system. J. Commun. Technol. Electron. 59(11), 1280\u20131288 (2014). https:\/\/doi.org\/10.1134\/S1064226914110059","journal-title":"J. Commun. Technol. Electron."},{"issue":"1","key":"26_CR10","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1159\/000515346","volume":"5","author":"G Fagherazzi","year":"2021","unstructured":"Fagherazzi, G., Fischer, A., Ismael, M., Despotovic, V.: Voice for health: the use of vocal biomarkers from research to clinical practice. Digital Biomarkers 5(1), 78\u201388 (2021). https:\/\/doi.org\/10.1159\/000515346","journal-title":"Digital Biomarkers"},{"key":"26_CR11","doi-asserted-by":"publisher","unstructured":"Favaro, A., et al.: Interpretable speech features vs. DNN embeddings: What to use in the automatic assessment of Parkinson\u2019s disease in multi-lingual scenarios. Comput. Biol. Med. 166, 107559 (2023). https:\/\/doi.org\/10.1016\/j.compbiomed.2023.107559","DOI":"10.1016\/j.compbiomed.2023.107559"},{"key":"26_CR12","doi-asserted-by":"publisher","unstructured":"Harar, P., Alonso-Hernandezy, J.B., Mekyska, J., Galaz, Z., Burget, R., Smekal, Z.: Voice Pathology Detection Using Deep Learning: a Preliminary Study. In: 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI), pp. 10\u201312. IEEE (2017). https:\/\/doi.org\/10.1109\/IWOBI.2017.7985525","DOI":"10.1109\/IWOBI.2017.7985525"},{"key":"26_CR13","doi-asserted-by":"publisher","unstructured":"Harar, P., Galaz, Z., Alonso-Hernandez, J.B., Mekyska, J., Burget, R., Smekal, Z.: Towards robust voice pathology detection. Neural Comput. &. Applic. 32(20), 15747\u201315757 (2020). https:\/\/doi.org\/10.1007\/s00521-018-3464-7","DOI":"10.1007\/s00521-018-3464-7"},{"key":"26_CR14","doi-asserted-by":"publisher","unstructured":"Islam, R., Tarique, M.: A novel convolutional neural network based dysphonic voice detection algorithm using chromagram. Inter. J. Elect. Comput. En. (2088-8708) 12(5) (2022). https:\/\/doi.org\/10.11591\/ijece.v12i5.pp5511-5518","DOI":"10.11591\/ijece.v12i5.pp5511-5518"},{"issue":"2","key":"26_CR15","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.otohns.2010.05.026","volume":"143","author":"MM Johns","year":"2010","unstructured":"Johns, M.M., Sataloff, R.T., Merati, A.L., Rosen, C.A.: Article commentary: Shortfalls of the american academy of otolaryngology\u2013head and neck surgery\u2019s clinical practice guideline: Hoarseness (dysphonia). Otolaryngology-Head and Neck Surgery 143(2), 175\u2013177 (2010). https:\/\/doi.org\/10.1016\/j.otohns.2010.05.026","journal-title":"Otolaryngology-Head and Neck Surgery"},{"key":"26_CR16","doi-asserted-by":"publisher","unstructured":"de\u00a0Jong, F.I.C.R.S., Kooijman, P.G.C., Thomas, G., Huinck, W.J., Graamans, K., Schutte, H.K.: Epidemiology of Voice Problems in Dutch Teachers. Folia Phoniatr. Logop. 58(3), 186\u2013198 (Apr 2006). https:\/\/doi.org\/10.1159\/000091732","DOI":"10.1159\/000091732"},{"key":"26_CR17","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.asoc.2014.03.036","volume":"21","author":"S Jothilakshmi","year":"2014","unstructured":"Jothilakshmi, S.: Automatic system to detect the type of voice pathology. Appl. Soft Comput. 21, 244\u2013249 (2014). https:\/\/doi.org\/10.1016\/j.asoc.2014.03.036","journal-title":"Appl. Soft Comput."},{"key":"26_CR18","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-642-35292-8_11","volume-title":"Advances in Speech and Language Technologies for Iberian Languages","author":"D Mart\u00ednez","year":"2012","unstructured":"Mart\u00ednez, D., Lleida, E., Ortega, A., Miguel, A., Villalba, J.: Voice pathology detection on the saarbr\u00fccken voice database with calibration and fusion of scores using multifocal toolkit. In: Torre Toledano, D., et al. (eds.) IberSPEECH 2012. CCIS, vol. 328, pp. 99\u2013109. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35292-8_11"},{"issue":"1","key":"26_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2458-9-370","volume":"9","author":"E Nerri\u00e8re","year":"2009","unstructured":"Nerri\u00e8re, E., Vercambre, M.N., Gilbert, F., Kovess-Masf\u00e9ty, V.: Voice disorders and mental health in teachers: a cross-sectional nationwide study. BMC Public Health 9(1), 1\u20138 (2009). https:\/\/doi.org\/10.1186\/1471-2458-9-370","journal-title":"BMC Public Health"},{"issue":"1","key":"26_CR20","first-page":"041","volume":"30","author":"HJ Park","year":"2021","unstructured":"Park, H.J., Shin, B.J.: Usefulness of glottal inverse filtering analysis in pathological voice1. J. Speech 30(1), 041\u2013048 (2021)","journal-title":"J. Speech"},{"key":"26_CR21","doi-asserted-by":"publisher","unstructured":"Pedregosa, F., et\u00a0al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011). https:\/\/doi.org\/10.48550\/arXiv.1201.0490","DOI":"10.48550\/arXiv.1201.0490"},{"key":"26_CR22","doi-asserted-by":"publisher","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust Speech Recognition via Large-Scale Weak Supervision. arXiv (Dec 2022). https:\/\/doi.org\/10.48550\/arXiv.2212.04356","DOI":"10.48550\/arXiv.2212.04356"},{"key":"26_CR23","unstructured":"Ravanelli, M., et al.: SpeechBrain: A general-purpose speech toolkit arXiv:2106.04624 (2021)"},{"issue":"2","key":"26_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjoto.2021.103327","volume":"43","author":"J Reid","year":"2022","unstructured":"Reid, J., Parmar, P., Lund, T., Aalto, D.K., Jeffery, C.C.: Development of a machine-learning based voice disorder screening tool. Am. J. Otolaryngol. 43(2), 103327 (2022). https:\/\/doi.org\/10.1016\/j.amjoto.2021.103327","journal-title":"Am. J. Otolaryngol."},{"key":"26_CR25","doi-asserted-by":"publisher","first-page":"14915","DOI":"10.1109\/ACCESS.2023.3243986","volume":"11","author":"D Ribas","year":"2023","unstructured":"Ribas, D., Pastor, M.A., Miguel, A., Mart\u00ednez, D., Ortega, A., Lleida, E.: Automatic voice disorder detection using self-supervised representations. IEEE Access 11, 14915\u201314927 (2023). https:\/\/doi.org\/10.1109\/ACCESS.2023.3243986","journal-title":"IEEE Access"},{"key":"26_CR26","unstructured":"Roy, N., Merrill, R.M., Thibeault, S., Parsa, R.A., Gray, S.D., Smith, E.M.: Prevalence of Voice Disorders in Teachers and the General Population. ASHA Wire (Apr 2004). https:\/\/pubs.asha.org\/doi\/10.1044\/1092-4388%282004\/023%29"},{"key":"26_CR27","doi-asserted-by":"publisher","unstructured":"Stachler, R.J., et\u00a0al.: Clinical practice guideline: Hoarseness (dysphonia) (update). Otolaryngology\u2013Head and Neck Surgery 158(S1), S1\u2013S42 (2018).https:\/\/doi.org\/10.1177\/0194599817751030","DOI":"10.1177\/0194599817751030"},{"key":"26_CR28","doi-asserted-by":"publisher","unstructured":"Sztah\u00f3, D., Kiss, G., Tulics, M.G.: Deep learning solution for pathological voice detection using lstm-based autoencoder hybrid with multi-task learning. In: BIOSIGNALS, pp. 135\u2013141 (2021). https:\/\/doi.org\/10.5220\/0010193101350141","DOI":"10.5220\/0010193101350141"},{"issue":"2","key":"26_CR29","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s10772-019-09592-y","volume":"22","author":"MG Tulics","year":"2019","unstructured":"Tulics, M.G., Vicsi, K.: The automatic assessment of the severity of dysphonia. Int. J. Speech Technol. 22(2), 341\u2013350 (2019). https:\/\/doi.org\/10.1007\/s10772-019-09592-y","journal-title":"Int. J. Speech Technol."},{"key":"26_CR30","unstructured":"unknown: Voice disorders. https:\/\/www.hopkinsmedicine.org\/health\/conditions-and-diseases\/voice-disorders"},{"key":"26_CR31","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention Is All You Need. arXiv (Jun 2017). https:\/\/doi.org\/10.48550\/arXiv.1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"26_CR32","doi-asserted-by":"publisher","first-page":"16246","DOI":"10.1109\/ACCESS.2018.2816338","volume":"6","author":"L Verde","year":"2018","unstructured":"Verde, L., De Pietro, G., Sannino, G.: Voice disorder identification by using machine learning techniques. IEEE Access 6, 16246\u201316255 (2018). https:\/\/doi.org\/10.1109\/ACCESS.2018.2816338","journal-title":"IEEE Access"},{"issue":"7","key":"26_CR33","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1093\/occmed\/kqg113","volume":"53","author":"NR Williams","year":"2024","unstructured":"Williams, N.R.: Occupational groups at risk of voice disorders: a review of the literature. Occup. Med. 53(7), 456\u2013460 (2024). https:\/\/doi.org\/10.1093\/occmed\/kqg113","journal-title":"Occup. Med."},{"key":"26_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2023.06.006","author":"B van der Woerd","year":"2023","unstructured":"van der Woerd, B., et al.: A machine-learning algorithm for the automated perceptual evaluation of dysphonia severity. J. Voice (2023). https:\/\/doi.org\/10.1016\/j.jvoice.2023.06.006","journal-title":"J. Voice"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77961-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T16:06:52Z","timestamp":1736438812000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77961-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031779602","9783031779619"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77961-9_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgrade","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Serbia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/specom2024.ftn.uns.ac.rs\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}