{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T05:43:00Z","timestamp":1772775780207,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030260606","type":"print"},{"value":"9783030260613","type":"electronic"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-26061-3_34","type":"book-chapter","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T23:03:54Z","timestamp":1565305434000},"page":"327-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Automatic Recognition of Speaker Age and Gender Based on Deep Neural Networks"],"prefix":"10.1007","author":[{"given":"Maxim","family":"Markitantov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oxana","family":"Verkholyak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,24]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Ranzato, M., Hinton, G.: Modeling pixel means and covariances using factorized third-order Boltzmann machines. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2551\u20132558 (2010)","DOI":"10.1109\/CVPR.2010.5539962"},{"key":"34_CR2","unstructured":"Lee, H., Ekanadham, C., Ng, A.: Sparse deep belief net model for visual area V2. In: Proceedings of the 20th International Conference on Neural Information Processing Systems, pp. 873\u2013880 (2007)"},{"key":"34_CR3","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G Dahl","year":"2012","unstructured":"Dahl, G., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20, 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Deselaers, T., Hasan, S., Bender, O., Ney, H.: A deep learning approach to machine transliteration. In: Proceedings of the Fourth Workshop on Statistical Machine Translation, pp. 233\u2013241 (2009)","DOI":"10.3115\/1626431.1626476"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Yu, D., Wang, S., Karam, Z., Deng, L.: Language recognition using deep-structured conditional random fields. In: Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 5030\u20135033 (2010)","DOI":"10.1109\/ICASSP.2010.5495072"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The INTERSPEECH 2010 paralinguistic challenge. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, pp. 2794\u20132797 (2010)","DOI":"10.21437\/Interspeech.2010-739"},{"key":"34_CR7","unstructured":"Burkhardt, F., Eckert, M., Johannsen, W., Stegmann, J.: A database of age and gender annotated telephone speech. In: Proceedings of 7th International Conference on Language Resources and Evaluation (LREC 2010) (2010)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: openSMILE - the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the ACM Multimedia 2010 International Conference, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Kockmann, M., Burget, L., Cernock\u00fd, J.: Brno University of Technology system for Interspeech 2010 paralinguistic challenge. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, pp. 2822\u20132825 (2010)","DOI":"10.21437\/Interspeech.2010-746"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Meinedo, H., Trancoso, I.: Age and gender classification using fusion of acoustic and prosodic features. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, pp. 2818\u20132821 (2010)","DOI":"10.21437\/Interspeech.2010-745"},{"issue":"1","key":"34_CR11","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.csl.2012.01.008","volume":"27","author":"M Li","year":"2013","unstructured":"Li, M., Han, K., Narayanan, S.: Automatic speaker age and gender recognition using acoustic and prosodic level information fusion. Comput. Speech Lang. 27(1), 151\u2013167 (2013)","journal-title":"Comput. Speech Lang."},{"key":"34_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.compeleceng.2016.06.002","volume":"53","author":"E Y\u00fccesoy","year":"2016","unstructured":"Y\u00fccesoy, E., Nabiyev, V.: A new approach with score-level fusion for the classification of a speaker age and gender. Comput. Electr. Eng. 53, 29\u201339 (2016)","journal-title":"Comput. Electr. Eng."},{"key":"34_CR13","unstructured":"R\u00f3wnicka, J., Kacprzak, S.: Speaker age classification and regression using i-vectors. In: Proceedings of the 17th Annual Conference of the International Speech Communication Association (INTERSPEECH 2016): Understanding Speech Processing in Humans and Machines, pp. 1402\u20131406 (2016)"},{"key":"34_CR14","unstructured":"Sadjadi, S., Slaney, M., Heck, L.: MSR identity toolbox v1.0: a Matlab toolbox for speaker-recognition research. Speech Lang. Process. Tech. Committee Newsl. 1, 1\u201332 (2013)"},{"key":"34_CR15","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1016\/j.knosys.2016.10.008","volume":"115","author":"Z Qawaqneh","year":"2016","unstructured":"Qawaqneh, Z., Abumallouh, A., Barkana, B.: Deep neural network framework and transformed MFCCs for speaker\u2019s age and gender classification. Knowl.-Based Syst. 115, 5\u201314 (2016)","journal-title":"Knowl.-Based Syst."},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Abumallouh, A., Qawaqneh, Z., Barkana, B.: New transformed features generated by deep bottleneck extractor and a GMM-UBM classifier for speaker age and gender classification. In: Neural Computing and Applications, vol. 30, no. 8, pp. 2581\u20132593 (2017)","DOI":"10.1007\/s00521-017-2848-4"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Ghahremani, P., et al.: End-to-end deep neural network age estimation. In: Proceedings of the 19th Annual Conference of the International Speech Communication Association, INTERSPEECH 2018, pp. 277\u2013281 (2018)","DOI":"10.21437\/Interspeech.2018-2015"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-Vectors: robust DNN embeddings for speaker recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Abumallouh, A., Qawaqneh, Z., Barkana, B.: Deep neural network combined posteriors for speakers\u2019 age and gender classification. In: Annual Connecticut Conference on Industrial Electronics, Technology & Automation (CT-IETA), pp. 1\u20135 (2016)","DOI":"10.1109\/CT-IETA.2016.7868251"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in Python. In: Proceedings of the 14th python in science conference, pp. 18\u201324 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"34_CR21","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch (2017)"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Bocklet, T., Stemmer, G., Zei\u00dfler, V., Noeth, E.: Age and gender recognition based on multiple systems - early vs. late fusion. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, pp. 2830\u20132833 (2010)","DOI":"10.21437\/Interspeech.2010-748"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Le, T., Tran, D., Huang, X., Sharma, D.: Fuzzy support vector machines for age and gender classification. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, pp. 2806\u20132809 (2010)","DOI":"10.21437\/Interspeech.2010-742"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Gajsek, R., \u017dibert, J., Justin, T., \u0160truc, V., Vesnicer, B., Mihelic, F.: Gender and affect recognition based on GMM and GMM-UBM modeling with relevance MAP estimation. In: Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010, pp. 2810\u20132813 (2010)","DOI":"10.21437\/Interspeech.2010-743"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-26061-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T10:29:26Z","timestamp":1664101766000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26061-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030260606","9783030260613"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26061-3_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 July 2019","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":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turkey","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"57","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"66% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}