{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T19:56:22Z","timestamp":1759694182953,"version":"3.37.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-99579-3_51","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"490-500","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["How Good Is Your Model \u2018Really\u2019? On \u2018Wildness\u2019 of the In-the-Wild Speech-Based Affect Recognisers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1983-8140","authenticated-orcid":false,"given":"Vedhas","family":"Pandit","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maximilian","family":"Schmitt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Cummins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Franz","family":"Graf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucas","family":"Paletta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"51_CR1","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B.: A database of German emotional speech. In: Proceedings of the 9th EUROSPEECH, pp. 1517\u20131520 (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"51_CR2","doi-asserted-by":"crossref","unstructured":"Coutinho, E., Deng, J., Schuller, B.: Transfer learning emotion manifestation across music and speech. In: Proceedings of the IJCNN, Beijing, China, pp. 3592\u20133598. IEEE (2014)","DOI":"10.1109\/IJCNN.2014.6889814"},{"key":"51_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Xia, R., Zhang, Z., Liu, Y., Schuller, B.: Introducing shared-hidden-layer autoencoders for transfer learning and their application in acoustic emotion recognition. In: Proceedings of the 39th ICASSP, Florence, Italy, pp. 4851\u20134855. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6854517"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Zhang, Z., Marchi, E., Schuller, B.: Sparse autoencoder-based feature transfer learning for speech emotion recognition. In: Proceedings of the 5th HUMAINE Association Conference on ACII, Geneva, Switzerland, pp. 511\u2013516. IEEE (2013)","DOI":"10.1109\/ACII.2013.90"},{"issue":"2","key":"51_CR5","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2016","unstructured":"Eyben, F., et al.: The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE Trans. Affect. Comput. 7(2), 190\u2013202 (2016)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"51_CR6","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Paletta, L., Schuller, B.: The acoustics of eye contact - detecting visual attention from conversational audio cues. In: Proceedings of the 6th Workshop on Eye Gaze in Intelligent Human Machine Interaction: Gaze in Multimodal Interaction (GAZEIN) at 15th ICMI, Sydney, Australia, pp. 7\u201312. ACM (2013)","DOI":"10.1145\/2535948.2535949"},{"key":"51_CR7","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Gro\u00df, F., Schuller, B.: Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM MM 2013, Barcelona, Spain, pp. 835\u2013838. ACM (2013). (Honorable Mention (2nd place) in the ACM MM 2013 Open-source Software Competition, acceptance rate: 28%, $$>200$$>200 citations)","DOI":"10.1145\/2502081.2502224"},{"key":"51_CR8","doi-asserted-by":"crossref","unstructured":"Grimm, M., Kroschel, K.: Evaluation of natural emotions using self assessment manikins. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 381\u2013385 (2005)","DOI":"10.1109\/ASRU.2005.1566530"},{"issue":"1","key":"51_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(1), 255\u2013268 (1989)","journal-title":"Biometrics"},{"key":"51_CR10","doi-asserted-by":"crossref","unstructured":"Mariooryad, S., Busso, C.: Analysis and compensation of the reaction lag of evaluators in continuous emotional annotations. In: Affective Computing and Intelligent Interaction (ACII), pp. 85\u201390 (2013)","DOI":"10.1109\/ACII.2013.21"},{"key":"51_CR11","doi-asserted-by":"crossref","unstructured":"Ng, H.W., Nguyen, V.D., Vonikakis, V., Winkler, S.: Deep learning for emotion recognition on small datasets using transfer learning. In: Proceedings of the 17th ICMI, pp. 443\u2013449. ACM (2015)","DOI":"10.1145\/2818346.2830593"},{"key":"51_CR12","unstructured":"Paeschke, A., Kienast, M., Sendlmeier, W.F.: F0-contours in emotional speech. In: Proceedings of the 14th International Congress of Phonetic Sciences, vol. 2, pp. 929\u2013932 (1999)"},{"key":"51_CR13","doi-asserted-by":"crossref","unstructured":"Pandit, V., et al.: Tracking authentic and in-the-wild emotions using speech. In: Proceedings of the 1st ACII Asia 2018, Beijing, P. R. China. AAAC\/IEEE (2018)","DOI":"10.1109\/ACIIAsia.2018.8470340"},{"key":"51_CR14","doi-asserted-by":"crossref","unstructured":"Pantic, M., Sebe, N., Cohn, J.F., Huang, T.: Affective multimodal human-computer interaction. In: Proceedings of the 13th ACM MM, Multimedia 2005, Singapore, pp. 669\u2013676. ACM (2005)","DOI":"10.1145\/1101149.1101299"},{"key":"51_CR15","unstructured":"Ringeval, F., et al.: AVEC 2017 - real-life depression, and affect recognition workshop and challenge. In: Ringeval, F., Valstar, M., Gratch, J., Schuller, B., Cowie, R., Pantic, M. (eds.) Proceedings of the 7th International Workshop on Audio\/Visual Emotion Challenge (AVEC 2017) at 25th ACM MM, Mountain View, CA, pp. 3\u20139. ACM (2017). 6 p"},{"key":"51_CR16","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: 10th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2013), Shanghai, P. R. China, pp. 1\u20138. IEEE (2013)","DOI":"10.1109\/FG.2013.6553805"},{"key":"51_CR17","first-page":"3370","volume":"18","author":"M Schmitt","year":"2017","unstructured":"Schmitt, M., Schuller, B.: openXBOW - Introducing the passau open-source crossmodal bag-of-words toolkit. J. Mach. Learn. Res. 18, 3370\u20133374 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"51_CR18","doi-asserted-by":"crossref","unstructured":"Schmitt, M., Ringeval, F., Schuller, B.: At the border of acoustics and linguistics: bag-of-audio-words for the recognition of emotions in speech. In: Proceedings of the 17th INTERSPEECH, San Francisco, CA, pp. 495\u2013499. ISCA (2016)","DOI":"10.21437\/Interspeech.2016-1124"},{"issue":"2","key":"51_CR19","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1177\/0038038503037002006","volume":"37","author":"S Speer","year":"2003","unstructured":"Speer, S., Hutchby, I.: From ethics to analytics: aspects of participants\u2019 orientations to the presence and relevance of recording devices. Sociology 37(2), 315\u2013337 (2003)","journal-title":"Sociology"},{"key":"51_CR20","doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., et al.: Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network. In: Proceedings of the 41st ICASSP, Shanghai, P. R. China, pp. 5200\u20135204. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472669"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T05:00:17Z","timestamp":1661835617000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_51","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}