{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:53:05Z","timestamp":1753602785304},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030260606"},{"type":"electronic","value":"9783030260613"}],"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_10","type":"book-chapter","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T19:03:54Z","timestamp":1565291034000},"page":"93-102","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Time-Continuous Emotion Recognition Using Spectrogram Based CNN-RNN Modelling"],"prefix":"10.1007","author":[{"given":"Dmitrii","family":"Fedotov","sequence":"first","affiliation":[]},{"given":"Bobae","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Alexey","family":"Karpov","sequence":"additional","affiliation":[]},{"given":"Wolfgang","family":"Minker","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,24]]},"reference":[{"key":"10_CR1","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: 2017 International Conference on Platform Technology and Service (PlatCon), pp. 1\u20135. IEEE (2017)","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Cai, D., Ni, Z., Liu, W., Cai, W., Li, G.: End-to-end deep learning framework for speech paralinguistics detection based on perception aware spectrum. In: Proceedings of Interspeech 2017, pp. 3452\u20133456 (2017)","DOI":"10.21437\/Interspeech.2017-1445"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Dieleman, S., Schrauwen, B.: End-to-end learning for music audio. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6964\u20136968. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854950"},{"issue":"3","key":"10_CR4","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M Ayadi El","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"10_CR5","doi-asserted-by":"crossref","unstructured":"Fedotov, D., Ivanko, D., Sidorov, M., Minker, W.: Contextual dependencies in time-continuous multidimensional affect recognition. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2018) (2018). Accepted paper","DOI":"10.1007\/978-3-319-66471-2_7"},{"key":"10_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-319-66471-2_7","volume-title":"Interactive Collaborative Robotics","author":"D Fedotov","year":"2017","unstructured":"Fedotov, D., Sidorov, M., Minker, W.: Context-awared models in time-continuous multidimensional affect recognition. In: Ronzhin, A., Rigoll, G., Meshcheryakov, R. (eds.) ICR 2017. LNCS (LNAI), vol. 10459, pp. 59\u201366. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66471-2_7"},{"key":"10_CR7","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Khorrami, P., Le Paine, T., Brady, K., Dagli, C., Huang, T.S.: How deep neural networks can improve emotion recognition on video data. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 619\u2013623. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"10_CR9","doi-asserted-by":"publisher","first-page":"255","DOI":"10.2307\/2532051","volume":"45","author":"I Lawrence","year":"1989","unstructured":"Lawrence, I., Lin, K.: A concordance correlation coefficient to evaluate reproducibility. Biometrics 45, 255\u2013268 (1989)","journal-title":"Biometrics"},{"issue":"8","key":"10_CR10","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao, Q., Dong, M., Huang, Z., Zhan, Y.: Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans. Multimedia 16(8), 2203\u20132213 (2014)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"10_CR11","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1109\/TAFFC.2016.2531664","volume":"8","author":"A Mencattini","year":"2017","unstructured":"Mencattini, A., Martinelli, E., Ringeval, F., Schuller, B., Di Natale, C.: Continuous estimation of emotions in speech by dynamic cooperative speaker models. IEEE Trans. Affect. Comput. 8(3), 314\u2013327 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Miehle, J., Yoshino, K., Pragst, L., Ultes, S., Nakamura, S., Minker, W.: Cultural communication idiosyncrasies in human-computer interaction. In: Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pp. 74\u201379 (2016)","DOI":"10.18653\/v1\/W16-3610"},{"key":"10_CR13","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.patrec.2014.11.007","volume":"66","author":"F Ringeval","year":"2015","unstructured":"Ringeval, F., et al.: Prediction of asynchronous dimensional emotion ratings from audiovisual and physiological data. Pattern Recognit. Lett. 66, 22\u201330 (2015)","journal-title":"Pattern Recognit. Lett."},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Ringeval, F., Sonderegger, A., Sauer, J., Lalanne, D.: Introducing the Recola multimodal corpus of remote collaborative and affective interactions. In: 2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG), pp. 1\u20138. IEEE (2013)","DOI":"10.1109\/FG.2013.6553805"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Weiss, R.J., Senior, A., Wilson, K.W., Vinyals, O.: Learning the speech front-end with raw waveform CLDNNs. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-1"},{"key":"10_CR16","unstructured":"Sidorov, M., Schmitt, A., Semenkin, E., Minker, W.: Could speaker, gender or age awareness be beneficial in speech-based emotion recognition? In: (Chair), N.C.C., Choukri, K. et al. (eds.) Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016), Paris, France. European Language Resources Association (ELRA), May 2016"},{"issue":"2","key":"10_CR17","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26\u201331 (2012)","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., et al.: Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5200\u20135204. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"10_CR19","doi-asserted-by":"crossref","unstructured":"Valstar, M., et al.: Avec 2016: depression, mood, and emotion recognition workshop and challenge. In: Proceedings of the 6th International Workshop on Audio\/Visual Emotion Challenge, pp. 3\u201310. ACM (2016)","DOI":"10.1145\/2988257.2988258"},{"key":"10_CR20","unstructured":"Vogt, T.: Real-time automatic emotion recognition from speech (2010)"}],"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_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T06:28:26Z","timestamp":1664087306000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26061-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030260606","9783030260613"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26061-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}