{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:20:00Z","timestamp":1767313200594,"version":"3.48.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031949005","type":"print"},{"value":"9783031949012","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-94901-2_1","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:15:51Z","timestamp":1767312951000},"page":"3-13","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Nonperiodic Pathologic Voice Signals Classification Using Mel-Spectrogram and VGGish"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0618-4627","authenticated-orcid":false,"given":"Joana Filipa Teixeira","family":"Fernandes","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6485-6786","authenticated-orcid":false,"given":"Jo\u00e3o Viana","family":"Pinto","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7291-6163","authenticated-orcid":false,"given":"Carla Pinto","family":"Moura","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7339-8409","authenticated-orcid":false,"given":"Helena","family":"Vilarinho","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-826X","authenticated-orcid":false,"given":"Felipe","family":"Teixeira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4260-9677","authenticated-orcid":false,"given":"Diamantino","family":"Freitas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6679-5702","authenticated-orcid":false,"given":"Jo\u00e3o Paulo","family":"Teixeira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"1_CR1","unstructured":"Titze, I. R. (1994). Workshop on acoustic voice analysis (pp. 1\u201336). National Center for Voice and Speech, America. [Online]. Available: http:\/\/scholar.google.com\/scholar?hl=en&btnG=Search&q=intitle:Workshop+on+Acoustic+Voice+Analysis#2"},{"issue":"1","key":"1_CR2","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/J.JVOICE.2020.03.006","volume":"36","author":"JM Miramont","year":"2022","unstructured":"Miramont, J. M., Restrepo, J. F., Codino, J., Jackson-Menaldi, C., & Schlotthauer, G. (2022). Voice signal typing using a pattern recognition approach. Journal of Voice, 36(1), 34\u201342. https:\/\/doi.org\/10.1016\/J.JVOICE.2020.03.006","journal-title":"Journal of Voice"},{"issue":"6","key":"1_CR3","doi-asserted-by":"publisher","first-page":"3710","DOI":"10.1121\/1.3397477","volume":"127","author":"A Sprecher","year":"2010","unstructured":"Sprecher, A., Olszewski, A., Jiang, J. J., & Zhang, Y. (2010). Updating signal typing in voice: Addition of type 4 signals. The Journal of the Acoustical Society of America, 127(6), 3710\u20133716. https:\/\/doi.org\/10.1121\/1.3397477","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"02","key":"1_CR4","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1055\/s-0035-1559678","volume":"95","author":"B Barsties","year":"2016","unstructured":"Barsties, B., Hoffmann, U., & Maryn, Y. (2016). Spektrografische Stimmtypenklassifizierung zur Beurteilung der Stimmqualit\u00e4t TT - The evaluation of voice quality via signal typing in voice using narrowband spectrograms. Laryngo- Rhino- Otologie, 95(02), 105\u2013111. https:\/\/doi.org\/10.1055\/s-0035-1559678","journal-title":"Laryngo- Rhino- Otologie"},{"issue":"5","key":"1_CR5","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1016\/J.JVOICE.2011.09.006","volume":"26","author":"SH Choi","year":"2012","unstructured":"Choi, S. H., Zhang, Y., Jiang, J. J., Bless, D. M., & Welham, N. V. (2012). Nonlinear dynamic-based analysis of severe dysphonia in patients with vocal fold scar and sulcus vocalis. Journal of Voice, 26(5), 566\u2013576. https:\/\/doi.org\/10.1016\/J.JVOICE.2011.09.006","journal-title":"Journal of Voice"},{"issue":"6","key":"1_CR6","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1016\/J.BSPC.2013.08.010","volume":"8","author":"C Fabris","year":"2013","unstructured":"Fabris, C., De Colle, W., & Sparacino, G. (2013). Voice disorders assessed by (cross-) sample entropy of electroglottogram and microphone signals. Biomedical Signal Processing and Control, 8(6), 920\u2013926. https:\/\/doi.org\/10.1016\/J.BSPC.2013.08.010","journal-title":"Biomedical Signal Processing and Control"},{"issue":"3","key":"1_CR7","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.jvoice.2014.08.018","volume":"29","author":"D Stone","year":"2015","unstructured":"Stone, D., et al. (2015). Voice outcomes after transoral laser microsurgery for early glottic cancer - Considering signal type and smoothed cepstral peak prominence. Journal of Voice, 29(3), 370\u2013381. https:\/\/doi.org\/10.1016\/j.jvoice.2014.08.018","journal-title":"Journal of Voice"},{"issue":"3","key":"1_CR8","doi-asserted-by":"publisher","first-page":"390.e1","DOI":"10.1016\/J.JVOICE.2014.08.007","volume":"29","author":"S Vaz Freitas","year":"2015","unstructured":"Vaz Freitas, S., Melo Pestana, P., Almeida, V., & Ferreira, A. (2015). Integrating voice evaluation: Correlation between acoustic and audio-perceptual measures. Journal of Voice, 29(3), 390.e1\u2013390.e7. https:\/\/doi.org\/10.1016\/J.JVOICE.2014.08.007","journal-title":"Journal of Voice"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Teixeira, D., Freitas, D., Braga, D., Barros, M. J., & Latsch, V. (2001). Phonetic events from the labeling the European Portuguese database for speech synthesis, FEUP\/IPB-DB. In Proceedings of Eurospeech\u201901 \u2013 International conference on spoken language processing (pp. 1707\u20131710). doi: 8790834100, 978-879083410-4","DOI":"10.21437\/Eurospeech.2001-400"},{"key":"1_CR10","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/J.ENGAPPAI.2019.03.027","volume":"82","author":"JA G\u00f3mez-Garc\u00eda","year":"2019","unstructured":"G\u00f3mez-Garc\u00eda, J. A., Moro-Vel\u00e1zquez, L., Mendes-Laureano, J., Castellanos-Dominguez, G., & Godino-Llorente, J. I. (2019). Emulating the perceptual capabilities of a human evaluator to map the GRB scale for the assessment of voice disorders. Engineering Applications of Artificial Intelligence, 82, 236\u2013251. https:\/\/doi.org\/10.1016\/J.ENGAPPAI.2019.03.027","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"Teixeira, J. P., Fernandes, J., Teixeira, F., & Fernandes, P. O. (2018). Acoustic analysis of chronic laryngitis statistical analysis of sustained speech parameters. In BIOSIGNALS 2018 - 11th international conference on bio-inspired systems and signal processing, proceedings; Part of 11th international joint conference on biomedical engineering systems and technologies, BIOSTEC 2018, vol. 4, pp. 168\u2013175. doi: https:\/\/doi.org\/10.5220\/0006586301680175","DOI":"10.5220\/0006586301680175"},{"issue":"6","key":"1_CR12","doi-asserted-by":"publisher","first-page":"947.e11","DOI":"10.1016\/J.JVOICE.2018.07.014","volume":"33","author":"S Hegde","year":"2019","unstructured":"Hegde, S., Shetty, S., Rai, S., & Dodderi, T. (2019). A survey on machine learning approaches for automatic detection of voice disorders. Journal of Voice, 33(6), 947.e11\u2013947.e33. https:\/\/doi.org\/10.1016\/J.JVOICE.2018.07.014","journal-title":"Journal of Voice"},{"key":"1_CR13","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/J.PROCS.2018.10.036","volume":"138","author":"V Guedes","year":"2018","unstructured":"Guedes, V., Junior, A., Fernandes, J., Teixeira, F., & Teixeira, J. P. (2018). Long short term memory on chronic laryngitis classification. Procedia Computer Science, 138, 250\u2013257. https:\/\/doi.org\/10.1016\/J.PROCS.2018.10.036","journal-title":"Procedia Computer Science"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Teixeira, J. P., & Freitas, D. (2003). Segmental durations predicted with a neural network. In Proceedings of Eurospeech\u201903 \u2013 International conference on spoken language pro-cessing (pp. 169\u2013172).","DOI":"10.21437\/Eurospeech.2003-91"},{"issue":"5","key":"1_CR15","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1111\/j.1365-2273.2004.00846.x","volume":"29","author":"PN Carding","year":"2004","unstructured":"Carding, P. N., Steen, I. N., Webb, A., Mackenzie, K., Deary, I. J., & Wilson, J. A. (2004). The reliability and sensitivity to change of acoustic measures of voice quality. Clinical Otolaryngology and Allied Sciences, 29(5), 538\u2013544. https:\/\/doi.org\/10.1111\/j.1365-2273.2004.00846.x","journal-title":"Clinical Otolaryngology and Allied Sciences"},{"issue":"5","key":"1_CR16","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1016\/j.jvoice.2011.08.013","volume":"26","author":"L D\u2019Alatri","year":"2012","unstructured":"D\u2019Alatri, L., Bussu, F., Scarano, E., Paludetti, G., & Marchese, M. R. (2012). Objective and subjective assessment of tracheoesophageal prosthesis voice outcome. Journal of Voice, 26(5), 607\u2013613. https:\/\/doi.org\/10.1016\/j.jvoice.2011.08.013","journal-title":"Journal of Voice"},{"issue":"9","key":"1_CR17","doi-asserted-by":"publisher","first-page":"1910","DOI":"10.1002\/lary.21915","volume":"121","author":"JJ Houlton","year":"2011","unstructured":"Houlton, J. J., et al. (2011). Voice outcomes following adult cricotracheal resection. Laryngoscope, 121(9), 1910\u20131914. https:\/\/doi.org\/10.1002\/lary.21915","journal-title":"Laryngoscope"},{"issue":"6","key":"1_CR18","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1016\/j.jvoice.2017.01.016","volume":"31","author":"LM Kopf","year":"2017","unstructured":"Kopf, L. M., et al. (2017). Pitch strength as an outcome measure for treatment of dysphonia. Journal of Voice, 31(6), 691\u2013696. https:\/\/doi.org\/10.1016\/j.jvoice.2017.01.016","journal-title":"Journal of Voice"},{"issue":"6","key":"1_CR19","first-page":"1977","volume":"7","author":"JY Lee","year":"2016","unstructured":"Lee, J. Y. (2016). Parameter estimations for signal type classification of Korean disordered voices. International Journal of Engineering and Technology, 7(6), 1977\u20131988.","journal-title":"International Journal of Engineering and Technology"},{"key":"1_CR20","volume-title":"Saarbruecken voice database","author":"M P\u00fctzer","year":"2007","unstructured":"P\u00fctzer, M., & Barry, W. J. (2007). Saarbruecken voice database. Institute of Phonetics at the University of Saarland. http:\/\/www.stimmdatenbank.coli.uni-saarland.de (accessed Nov. 05, 2021"},{"key":"1_CR21","doi-asserted-by":"publisher","first-page":"104805","DOI":"10.1016\/J.BSPC.2023.104805","volume":"85","author":"A Maity","year":"2023","unstructured":"Maity, A., Pathak, A., & Saha, G. (2023). Transfer learning based heart valve disease classification from Phonocardiogram signal. Biomedical Signal Processing and Control, 85, 104805. https:\/\/doi.org\/10.1016\/J.BSPC.2023.104805","journal-title":"Biomedical Signal Processing and Control"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1121\/1.1915893","volume":"8","author":"SSSJVEB Newman","year":"1937","unstructured":"Newman, S. S. S. J. V. E. B. (1937). A scale for the measurement of the psychological magnitude pitch. The Journal of the Acoustical Society of America, 8, 185\u2013190. https:\/\/doi.org\/10.1121\/1.1915893","journal-title":"The Journal of the Acoustical Society of America"},{"key":"1_CR23","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1016\/J.PROCS.2019.12.232","volume":"164","author":"J Fernandes","year":"2019","unstructured":"Fernandes, J., Silva, L., Teixeira, F., Guedes, V., Santos, J., & Teixeira, J. P. (2019). Parameters for vocal acoustic analysis - Cured database. Procedia Computer Science, 164, 654\u2013661. https:\/\/doi.org\/10.1016\/J.PROCS.2019.12.232","journal-title":"Procedia Computer Science"},{"issue":"9","key":"1_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/rs13091734","volume":"13","author":"S Khaleghian","year":"2021","unstructured":"Khaleghian, S., Ullah, H., Kr\u00e6mer, T., Hughes, N., Eltoft, T., & Marinoni, A. (2021). Sea ice classification of sar imagery based on convolution neural networks. Remote Sensing, 13(9), 1\u201320. https:\/\/doi.org\/10.3390\/rs13091734","journal-title":"Remote Sensing"},{"key":"1_CR25","doi-asserted-by":"publisher","unstructured":"Mascarenhas, S., & Agarwal, M. (2021). A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification. In Proceedings of the IEEE international conference on disruptive technologies for multi-disciplinary research and applications CENTCON 2021 (vol. 1, pp. 96\u201399). doi: https:\/\/doi.org\/10.1109\/CENTCON52345.2021.9687944","DOI":"10.1109\/CENTCON52345.2021.9687944"},{"issue":"5","key":"1_CR26","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"HC Shin","year":"2016","unstructured":"Shin, H. C., et al. (2016). Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging, 35(5), 1285\u20131298. https:\/\/doi.org\/10.1109\/TMI.2016.2528162","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"6","key":"1_CR27","first-page":"1","volume":"21","author":"M Diwakar","year":"2023","unstructured":"Diwakar, M., & Gupta, A. B. (2023). The robust feature extraction of audio signal by using VGGish model. The International Journal of Computer Science and Information Security, 21(6), 1\u201318.","journal-title":"The International Journal of Computer Science and Information Security"},{"key":"1_CR28","doi-asserted-by":"publisher","first-page":"158215","DOI":"10.1109\/ACCESS.2021.3131231","volume":"9","author":"H Samma","year":"2021","unstructured":"Samma, H., Suandi, S. A., Ismail, N. A., Sulaiman, S., & Ping, L. L. (2021). Evolving pre-trained CNN using two-layers optimizer for road damage detection from drone images. IEEE Access, 9, 158215\u2013158226. https:\/\/doi.org\/10.1109\/ACCESS.2021.3131231","journal-title":"IEEE Access"},{"key":"1_CR29","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/J.PROCS.2016.09.155","volume":"100","author":"JP Teixeira","year":"2016","unstructured":"Teixeira, J. P., & Gon\u00e7alves, A. (2016). Algorithm for Jitter and Shimmer measurement in pathologic voices. Procedia Computer Science, 100, 271\u2013279. https:\/\/doi.org\/10.1016\/J.PROCS.2016.09.155","journal-title":"Procedia Computer Science"}],"container-title":["Springer Proceedings in Business and Economics","Health Technologies and Demographic Challenges"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-94901-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:15:53Z","timestamp":1767312953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-94901-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031949005","9783031949012"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-94901-2_1","relation":{},"ISSN":["2198-7246","2198-7254"],"issn-type":[{"value":"2198-7246","type":"print"},{"value":"2198-7254","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDTHT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Demographic Transition, Health, and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salinas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ecuador","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 February 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 February 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdtht2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdtht.org\/index.php\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}