{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:25:37Z","timestamp":1756311937189,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031238031"},{"type":"electronic","value":"9783031238048"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-23804-8_15","type":"book-chapter","created":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T12:02:40Z","timestamp":1677326560000},"page":"181-193","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Study on\u00a0Far-Field Emotion Recognition Based on\u00a0Deep Convolutional Neural Networks"],"prefix":"10.1007","author":[{"given":"Panikos","family":"Heracleous","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasser","family":"Mohammad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Takai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keiji","family":"Yasuda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akio","family":"Yoneyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fumiaki","family":"Sugaya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,26]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid, O., Mohamed, A.R., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22, 1533\u20131545 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"15_CR2","unstructured":"Bielefeld, B.: Language identification using shifted delta cepstrum. In: Fourteenth Annual Speech Research Symposium (1994)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. J. Lang. Resour. Eval. 42, 335\u2013359 (2008)","DOI":"10.1007\/s10579-008-9076-6"},{"key":"15_CR4","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1093\/acprof:oso\/9780195387643.003.0008","volume-title":"Social Emotions in Nature and Artifact: Emotions in Human and Human-Computer Interaction","author":"C Busso","year":"2013","unstructured":"Busso, C., Bulut, M., Narayanan, S.: Toward effective automatic recognition systems of emotion in speech. In: Gratch, J., Marsella, S. (eds.) Social Emotions in Nature and Artifact: Emotions in Human and Human-Computer Interaction, pp. 110\u2013127. Oxford University Press, New York (2013)"},{"key":"15_CR5","unstructured":"Cristianini, N., S.-Taylor, J.: Support Vector Machines. Cambridge University Press, Cambridge (2000)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., R.T.: Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Ann. stat. 28(2), 337\u2013407 (2000)","DOI":"10.1214\/aos\/1016218223"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Ganapathy, S., Han, K., Thomas, S., Omar, M., Segbroeck, M.V., Narayanan, S.S.: Robust language identification using convolutional neural network features. In: Proceedings of Interspeech (2014)","DOI":"10.21437\/Interspeech.2014-419"},{"issue":"1","key":"15_CR8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3\u201342 (2006)","journal-title":"Mach. Learn."},{"key":"15_CR9","unstructured":"Ha, H.K., Kim, N.K., Seong, W.K., Kim, H.K.: Noise-Robust Speech Emotion Recognition Using Denoising Autoencoder. Audio Engineering Society Convention 140 (2016). http:\/\/www.aes.org\/e-lib\/browse.cfm?elib=18164"},{"key":"15_CR10","doi-asserted-by":"publisher","first-page":"457","DOI":"10.2478\/aoa-2013-0054","volume":"38","author":"C Huang","year":"2013","unstructured":"Huang, C., Chen, G., Yu, H., Bao, Y., Zhao, L.: Speech Emotion Recognition under White Noise. Arch. Acoust. 38, 457\u2013463 (2013)","journal-title":"Arch. Acoust."},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Huang, C.W., Narayanan, S.: Attention assisted discover of sub-utterance in speech emotion recognition. In: Proceedings of Interspeech, pp. 1387\u20131391 (2016)","DOI":"10.21437\/Interspeech.2016-448"},{"key":"15_CR12","series-title":"Lecture Notes in Electrical Engineering","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1007\/978-981-10-0557-2_44","volume-title":"Information Science and Applications (ICISA) 2016","author":"X-P Huynh","year":"2016","unstructured":"Huynh, X.-P., Tran, T.-D., Kim, Y.-G.: Convolutional neural network models for facial expression recognition using BU-3DFE database. In: Information Science and Applications (ICISA) 2016. LNEE, vol. 376, pp. 441\u2013450. Springer, Singapore (2016). https:\/\/doi.org\/10.1007\/978-981-10-0557-2_44"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kanagasundaram, A., Dean, D., Sridharan, S.: Improving PLDA speaker verification with limited development data. In: Proceedings of 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1684\u20131688 (2014)","DOI":"10.1109\/ICASSP.2014.6853881"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746\u20131751 (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"15_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097\u20131105. Curran Associates, Inc. (2012)"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Lim, W., Jang, D., Lee, T.: Speech emotion recognition using convolutional and recurrent neural networks. In: Proceedings of Signal and Information Processing Association Annual Summit and Conference (APSIPA) (2016)","DOI":"10.1109\/APSIPA.2016.7820699"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Liu, R.X.Y.: Using i-vector space model for emotion recognition. In: Proceedings of Interspeech, pp. 2227\u20132230 (2012)","DOI":"10.21437\/Interspeech.2012-128"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Metallinou, A., Lee, S., Narayanan, S.: Decision level combination of multiple modalities for recognition and analysis of emotional expression. In: Proceedings of 2010 IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP, pp. 2462\u20132465 (2010)","DOI":"10.1109\/ICASSP.2010.5494890"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Mohammad, Y., Matsumoto, K., Hoashi, K.: Deep feature learning and selection for activity recognition. In: Proceedings of the 33rd ACM\/SIGAPP Symposium On Applied Computing, pp. 926\u2013935. ACM SAC (2018)","DOI":"10.1145\/3167132.3167234"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Nakamura, S., Hiyane, K., Asano, F., Endo, T.: Sound Scene Data Collection in Real Acoustical Environments. J. Acoust. Soc. Japan 20(3), 225\u2013231 (1999)","DOI":"10.1250\/ast.20.225"},{"issue":"4","key":"15_CR21","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1007\/s005210070006","volume":"9","author":"J Nicholson","year":"2000","unstructured":"Nicholson, J., Takahashi, K., Nakatsu, R.: Emotion recognition in speech using neural networks. Neural Comput. Appl. 9(4), 290\u2013296 (2000)","journal-title":"Neural Comput. Appl."},{"issue":"2","key":"15_CR22","first-page":"101","volume":"6","author":"Y Pan","year":"2012","unstructured":"Pan, Y., Shen, P., Shen, L.: Speech emotion recognition using support vector machine. Int. J. Smart Home 6(2), 101\u2013108 (2012)","journal-title":"Int. J. Smart Home"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Pohjalainen, J., Ringeval, F., Zhang, Z., Schuller, B.: Spectral and cepstral audio noise reduction techniques in speech emotion recognition. In: Proceedings of ACM (2016)","DOI":"10.1145\/2964284.2967306"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Prabhavalkar, R., Alvarez, R., Parada, C., Nakkiran, P., Sainath, T.: Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks. In: Proceedings of 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4704\u20134708 (2015)","DOI":"10.1109\/ICASSP.2015.7178863"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Prince, S., Elder, J.: Probabilistic linear discriminant analysis for inferences about identity. In: Proceedings of International Conference on Computer Vision, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4409052"},{"key":"15_CR26","doi-asserted-by":"publisher","first-page":"2352","DOI":"10.1162\/neco_a_00990","volume":"29","author":"W Rawat","year":"2017","unstructured":"Rawat, W., Wang, Z.: Deep convolutional neural networks for image classification: a comprehensive review. Neural Commun. 29, 2352\u20132449 (2017)","journal-title":"Neural Commun."},{"key":"15_CR27","unstructured":"Romero, D.G., Wilson, C.E.: Analysis of i-vector length normalization in speaker recognition systems. In: Proceedings of INTERSPEECH, pp. 249\u2013252 (2011)"},{"issue":"4","key":"15_CR28","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.specom.2011.11.004","volume":"54","author":"M Sahidullah","year":"2012","unstructured":"Sahidullah, M., Saha, G.: Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition. Speech Commun. 54(4), 543\u2013565 (2012)","journal-title":"Speech Commun."},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Schuller, B., Arsic, D., Wallhoff, F., Rigoll, G.: Emotion recognition in the noise applying large acoustic feature sets. In: Proceedings of 3rd International Conference on Speech Prosody, pp. 276\u2013279 (2006)","DOI":"10.21437\/SpeechProsody.2006-150"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Schuller, B., Rigoll, G., Lang, M.: Hidden markov model-based speech emotion recognition. In: Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). I, 401\u2013404 (2003)","DOI":"10.1109\/ICME.2003.1220939"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Stuhlsatz, A., Meyer, C., Eyben, F., Zielke1, T., Meier, G., Schuller, B.: Deep neural networks for acoustic emotion recognition: raising the benchmarks. In: Proceedings of 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5688\u20135691 (2011)","DOI":"10.1109\/ICASSP.2011.5947651"},{"issue":"2","key":"15_CR32","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1121\/1.412224","volume":"97","author":"Y Suzuki","year":"1995","unstructured":"Suzuki, Y., Asano, F., Kim, H., Sone, T.: An optimum computer-generated pulse signal suitable for the measurement of very long impulse responses. J. Acoust. Soc. Am. 97(2), 1119\u20131123 (1995)","journal-title":"J. Acoust. Soc. Am."},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"T.-Carrasquillo, P., et al.: Approaches to language identification using gaussian mixture models and shifted delta cepstral features. In: Proceedings of ICSLP2002-INTERSPEECH2002, pp. 16\u201320 (2002)","DOI":"10.21437\/ICSLP.2002-74"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Tang, H., Chu, S., Johnson, M.H.: Emotion recognition from speech via boosted gaussian mixture models. In: Proceedings of 2009 IEEE International Conference on Multimedia and Expo (ICME), pp. 294\u2013297 (2009)","DOI":"10.1109\/ICME.2009.5202493"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Tawari, A., Trivedi, M.: Speech emotion analysis in noisy real-world environment. In: Proceedings of International Conference on Pattern Recognition, pp. 4605\u20134608 (2010)","DOI":"10.1109\/ICPR.2010.1132"},{"key":"15_CR36","doi-asserted-by":"crossref","unstructured":"Tzinis, E., Potamianos, A.: Segment-based emotion recognition using recurrent neural networks. In: Proceedings of 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 190\u2013195 (2017)","DOI":"10.1109\/ACII.2017.8273599"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Xia, R., Liu, Y.: Using i-vector space model for emotion recognition. In: Proceedings of INTERSPEECH, pp. 2227\u20132230 (2012)","DOI":"10.21437\/Interspeech.2012-128"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wu, J.: Speech emotion recognition with i-vector feature and RNN model. In: 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP) (2015)","DOI":"10.1109\/ChinaSIP.2015.7230458"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-23804-8_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T04:53:16Z","timestamp":1728967996000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-23804-8_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031238031","9783031238048"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-23804-8_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"26 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 March 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}