{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:00:19Z","timestamp":1740099619076,"version":"3.37.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030412982"},{"type":"electronic","value":"9783030412999"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-41299-9_34","type":"book-chapter","created":{"date-parts":[[2020,2,22]],"date-time":"2020-02-22T09:02:51Z","timestamp":1582362171000},"page":"435-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["A Segment Level Approach to Speech Emotion Recognition Using Transfer Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1956-2834","authenticated-orcid":false,"given":"Sourav","family":"Sahoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4318-1353","authenticated-orcid":false,"given":"Puneet","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6277-6267","authenticated-orcid":false,"given":"Balasubramanian","family":"Raman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5735-5254","authenticated-orcid":false,"given":"Partha Pratim","family":"Roy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,23]]},"reference":[{"key":"34_CR1","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: International Conference on Machine Learning (ICML), pp. 173\u2013182 (2016)"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Badshah, A.M., Ahmad, J., Rahim, N., Baik, S.W.: Speech emotion recognition from spectrograms with deep convolutional neural network. In: International Conference on Platform Technology and Service (PlatCon), pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Braun, M., Mainz, A., Chadowitz, R., Pfleging, B., Alt, F.: At your service: designing voice assistant personalities to improve automotive user interfaces. In: Proceedings of the CHI Conference on Human Factors in Computing Systems, p. 40. ACM (2019)","DOI":"10.1145\/3290605.3300270"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B.: A database of German emotional speech. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"4","key":"34_CR5","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Caruana, R., Lawrence, S., Giles, C.L.: Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In: Advances in Neural Information Processing Systems, pp. 402\u2013408 (2001)","DOI":"10.1109\/IJCNN.2000.857823"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: Computer Vision and Pattern Recognition (CVPR). IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Gideon, J., Khorram, S., Aldeneh, Z., Dimitriadis, D., Provost, E.M.: Progressive neural networks for transfer learning in emotion recognition. arXiv preprint arXiv:1706.03256 (2017)","DOI":"10.21437\/Interspeech.2017-1637"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., Tashev, I.: Speech emotion recognition using deep neural network and extreme learning machine. In: Fifteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 223\u2013227. ISCA (2014)","DOI":"10.21437\/Interspeech.2014-57"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 131\u2013135. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"34_CR12","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"34_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"34_CR14","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/BF00992553","volume":"5","author":"PR Kleinginna","year":"1981","unstructured":"Kleinginna, P.R., Kleinginna, A.M.: A categorized list of emotion definitions, with suggestions for a consensual definition. Motiv. Emot. 5, 345\u2013379 (1981)","journal-title":"Motiv. Emot."},{"key":"34_CR15","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"issue":"9\u201310","key":"34_CR16","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.specom.2011.06.004","volume":"53","author":"CC Lee","year":"2011","unstructured":"Lee, C.C., Mower, E., Busso, C., Lee, S., Narayanan, S.: Emotion recognition using a hierarchical binary decision tree approach. Speech Commun. 53(9\u201310), 1162\u20131171 (2011)","journal-title":"Speech Commun."},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Lee, J., Tashev, I.: High-level feature representation using recurrent neural network for speech emotion recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 1537\u20131540. ISCA (2015)","DOI":"10.21437\/Interspeech.2015-336"},{"issue":"5","key":"34_CR18","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The ryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in North American English. PLoS ONE 13(5), e0196391 (2018)","journal-title":"PLoS ONE"},{"key":"34_CR19","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML), pp. 807\u2013814 (2010)"},{"key":"34_CR20","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"},{"issue":"10","key":"34_CR21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S.J., Yang, Q.: A survey on transfer learning. Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009)","journal-title":"Trans. Knowl. Data Eng."},{"key":"34_CR22","unstructured":"Ping, W., et al.: Deep voice 3: scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654 (2017)"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Provost, E.M.: Identifying salient sub-utterance emotion dynamics using flexible units and estimates of affective flow. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3682\u20133686. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638345"},{"key":"34_CR24","unstructured":"Sahu, G.: Multimodal speech emotion recognition and ambiguity resolution. arXiv preprint arXiv:1904.06022 (2019)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Satt, A., Rozenberg, S., Hoory, R.: Efficient emotion recognition from speech using deep learning on spectrograms. In: Eighteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 1089\u20131093. ISCA (2017)","DOI":"10.21437\/Interspeech.2017-200"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Schuller, B., Rigoll, G., Lang, M.: Hidden Markov model-based speech emotion recognition. In: Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. II-1. IEEE (2003)","DOI":"10.1109\/ICME.2003.1220939"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Seehapoch, T., Wongthanavasu, S.: Speech emotion recognition using support vector machines. In: 5th International Conference on Knowledge and Smart Technology (KST), pp. 86\u201391. IEEE (2013)","DOI":"10.1109\/KST.2013.6512793"},{"key":"34_CR28","unstructured":"Shami, M.T., Kamel, M.S.: Segment-based approach to the recognition of emotions in speech. In: International Conference on Multimedia and Expo, pp. 4-pp. IEEE (2005)"},{"key":"34_CR29","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"9","key":"34_CR30","doi-asserted-by":"publisher","first-page":"2530","DOI":"10.1587\/transinf.2014EDL8038","volume":"97","author":"P Song","year":"2014","unstructured":"Song, P., Jin, Y., Zhao, L., Xin, M.: Speech emotion recognition using transfer learning. IEICE Trans. Inf. Syst. 97(9), 2530\u20132532 (2014)","journal-title":"IEICE Trans. Inf. Syst."},{"issue":"1","key":"34_CR31","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., et al.: Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5200\u20135204. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Yoon, S., Byun, S., Dey, S., Jung, K.: Speech emotion recognition using multi-hop attention mechanism. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2822\u20132826. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Yoon, S., Byun, S., Jung, K.: Multimodal speech emotion recognition using audio and text. In: Spoken Language Technology Workshop (SLT), pp. 112\u2013118. IEEE (2018)","DOI":"10.1109\/SLT.2018.8639583"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, W., Yu, J., Zou, Y.: An experimental study of speech emotion recognition based on deep convolutional neural networks. In: International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 827\u2013831. IEEE (2015)","DOI":"10.1109\/ACII.2015.7344669"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41299-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T08:10:23Z","timestamp":1665907823000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41299-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030412982","9783030412999"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41299-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"23 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"26 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"214","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":"125","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":"58% - 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":"2","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)"}},{"value":"for ACPR 2019 Workshops volume accepted 17 full papers and 6 short papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}