{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:06:02Z","timestamp":1742911562008,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030625788"},{"type":"electronic","value":"9783030625795"}],"license":[{"start":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:00:00Z","timestamp":1604361600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:00:00Z","timestamp":1604361600000},"content-version":"vor","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":[[2021]]},"DOI":"10.1007\/978-3-030-62579-5_23","type":"book-chapter","created":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T06:02:40Z","timestamp":1604296960000},"page":"332-344","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Age and Gender Recognition from Speech Using Deep Neural Networks"],"prefix":"10.1007","author":[{"given":"H\u00e9ctor A.","family":"S\u00e1nchez-Hevia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Gil-Pita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Utrilla-Manso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel","family":"Rosa-Zurera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,3]]},"reference":[{"key":"23_CR1","unstructured":"Abadi, M., Agarwal, A., Barham, P., et\u00a0al.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). http:\/\/tensorflow.org\/ . Software available from tensorflow.org"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Badshah, A., Ahmad, J., Rahim, N., Baik, S.: Speech emotion recognition from spectrograms with deep convolutional neural network. In: 2017 International Conference on Platform Technology and Service (PlatCon), pp. 1\u20135 (2017)","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Bahari, M., McLaren, M., Van\u00a0Leeuwen, D., et\u00a0al.: Age estimation from telephone speech using i-vectors. In: Proceedings of Interspeech 2012. Portland, USA (2012)","DOI":"10.21437\/Interspeech.2012-169"},{"key":"23_CR4","unstructured":"Bai, S., Kolter, J., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arxiv 2018. arXiv preprint arXiv:1803.01271"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Bhat, C., Mithum, B., Saxena, V., Kulkarni, V., Kopparapu, S.: Deploying usable speech enabled IVR systems for mass use. In: 2013 IEEE International Conference on Human Computer Interaction (ICHCI), pp. 1\u20135 (2013)","DOI":"10.1109\/ICHCI-IEEE.2013.6887794"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Cakir, E., Adavanne, S., Parascandolo, G., Drossos, K., Virtanen, T.: Convolutional recurrent neural networks for bird audio detection. In: 2017 25th European Signal Processing Conference (EUSIPCO), pp. 1744\u20131748 (2017)","DOI":"10.23919\/EUSIPCO.2017.8081508"},{"key":"23_CR7","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014). arXiv:1406.1078"},{"key":"23_CR8","unstructured":"Chollet, F., et\u00a0al.: Keras (2015). https:\/\/keras.io"},{"key":"23_CR9","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"521","author":"R Rumelhart","year":"1986","unstructured":"Rumelhart, R., et al.: Learning representations by back-propagating errors. Nature 521, 533\u2013536 (1986)","journal-title":"Nature"},{"key":"23_CR10","unstructured":"Foundation, M.: Common voice (2019). https:\/\/voice.mozilla.org"},{"issue":"1\u20132","key":"23_CR11","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/S0167-6393(97)00040-X","volume":"23","author":"A Gorin","year":"1997","unstructured":"Gorin, A., Riccardi, G., Wright, J.: How may i help you? Speech Commun. 23(1\u20132), 113\u2013127 (1997)","journal-title":"Speech Commun."},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Kalluri, S.B., Vijayasenan, D., Ganapathy, S.: A deep neural network based end to end model for joint height and age estimation from short duration speech. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007), pp. 6580\u20136584. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683397"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Kang, Y., Tsang, K.Y., Wong, K.W.Y.: The effect of speech rate on age estimation in conversational speech. Toronto Working Papers in Linguistics (TWPL) 42, 1\u201310 (2020)","DOI":"10.33137\/twpl.v42i1.33149"},{"key":"23_CR14","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"323","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 323, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Metze, F., Ajmera, J., Englert, R., Bub, U., et\u00a0al.: Comparison of four approaches to age and gender recognition for telephone applications. In: 2007 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2007), vol. 4, pp. IV\u20131089 (2007)","DOI":"10.1109\/ICASSP.2007.367263"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Minematsu, N., Sekiguchi, M., Hirose, K.: Automatic estimation of one\u2019s age with his\/her speech based upon acoustic modeling techniques of speakers. In: 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2002), vol.\u00a01, pp. I\u2013137 (2002)","DOI":"10.1109\/ICASSP.2002.5743673"},{"key":"23_CR17","unstructured":"Mohino-Herranz, I., Garc\u00eda-G\u00f3mez, J., Utrilla-Manso, M., Rosa-Zurera, M.: Precision maximization in anger detection in interactive voice response systems. In: 145th Convention of the Audio Engineering Society, p. 10090 (2018)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Neumann, M., Vu, N.T.: Attentive convolutional neural network based speech emotion recognition: A study on the impact of input features, signal length, and acted speech. arXiv preprint arXiv:1706.00612 (2017)","DOI":"10.21437\/Interspeech.2017-917"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Pandey, A., Wang, D.: TCNN: Temporal convolutional neural network for real-time speech enhancement in the time domain. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), pp. 6875\u20136879 (2019)","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Pappas, D., Androutsopoulos, I., Papageorgiou, H.: Anger detection in call center dialogues. In: 2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom), pp. 139\u2013144 (2015)","DOI":"10.1109\/CogInfoCom.2015.7390579"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Park, S.R., Lee, J.: A fully convolutional neural network for speech enhancement. arXiv preprint arXiv:1609.07132 (2016)","DOI":"10.21437\/Interspeech.2017-1465"},{"issue":"3","key":"23_CR22","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/BF02478291","volume":"9","author":"W Pitts","year":"1947","unstructured":"Pitts, W., McCulloch, W.: How we know universals the perception of auditory and visual forms. Bull. Math. Biophys. 9(3), 127\u2013147 (1947). https:\/\/doi.org\/10.1007\/BF02478291","journal-title":"Bull. Math. Biophys."},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Ranjan, S., Hansen, J.H.: Improved gender independent speaker recognition using convolutional neural network based bottleneck features. In: Proceedings of Interspeech, pp. 1009\u20131013 (2017)","DOI":"10.21437\/Interspeech.2017-1182"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Sanchez-Hevia, H., Gil-Pita, R., Utrilla-Manso, M., Rosa-Zurera, M.: Convolutional-recurrent neural network for age an gender prediction from speech. In: 2019 Signal Processing Symposium, Krakow (Poland), pp. 246\u2013249. IEEE (2019)","DOI":"10.1109\/SPS.2019.8881961"},{"issue":"105596","key":"23_CR25","first-page":"1","volume":"194","author":"S Sengupta","year":"2020","unstructured":"Sengupta, S., et al.: A review of deep learning with special emphasis on architectures, applications and recent trends. Knowl. Based Syst. 194(105596), 1\u201333 (2020)","journal-title":"Knowl. Based Syst."},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Xu, Y., Kong, Q., Wang, W., Plumbley, M.: Large-scale weakly supervised audio classification using gated convolutional neural network. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008), pp. 121\u2013125 (2018)","DOI":"10.1109\/ICASSP.2018.8461975"},{"key":"23_CR27","doi-asserted-by":"publisher","first-page":"22524","DOI":"10.1109\/ACCESS.2018.2816163","volume":"6","author":"R Zazo","year":"2018","unstructured":"Zazo, R., Nidadavolu, P., Chen, N., Gonzalez-Rodriguez, J., Dehak, N.: Age estimation in short speech utterances based on LSTM recurrent neural networks. IEEE Access 6, 22524\u201322530 (2018)","journal-title":"IEEE Access"},{"issue":"11","key":"23_CR28","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z.Q., Zheng, P., Xu, S.T., Wu, X.: Object detection with deep learning: a review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212\u20133232 (2019)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Advances in Intelligent Systems and Computing","Advances in Physical Agents II"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-62579-5_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T03:49:54Z","timestamp":1669434594000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-62579-5_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,3]]},"ISBN":["9783030625788","9783030625795"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-62579-5_23","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2020,11,3]]},"assertion":[{"value":"3 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WAF","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop of Physical Agents","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Alcal\u00e1 de Henares, Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"waf2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.robesafe.uah.es\/waf2020","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}