{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T11:56:51Z","timestamp":1778155011084,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1-2","license":[{"start":{"date-parts":[[2009,12,12]],"date-time":"2009-12-12T00:00:00Z","timestamp":1260576000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Multimodal User Interfaces"],"published-print":{"date-parts":[[2010,3]]},"DOI":"10.1007\/s12193-009-0032-6","type":"journal-article","created":{"date-parts":[[2009,12,11]],"date-time":"2009-12-11T11:42:08Z","timestamp":1260531728000},"page":"7-19","source":"Crossref","is-referenced-by-count":95,"title":["On-line emotion recognition in a 3-D activation-valence-time continuum using acoustic and linguistic cues"],"prefix":"10.1007","volume":"3","author":[{"given":"Florian","family":"Eyben","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"W\u00f6llmer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Graves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bj\u00f6rn","family":"Schuller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ellen","family":"Douglas-Cowie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roddy","family":"Cowie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,12,12]]},"reference":[{"key":"32_CR1","unstructured":"Batliner A, Steidl S, N\u00f6th E (2008) Releasing a thoroughly annotated and processed spontaneous emotional database: the FAU Aibo Emotion Corpus. In: Deviller\u00a0 L, Martin\u00a0JC, Cowie\u00a0R, Douglas-Cowie\u00a0E, Batliner\u00a0A (eds) Proc. of a satellite workshop of LREC 2008 on corpora for research on emotion and affect, pp\u00a028\u201331. Marrakesh"},{"issue":"2","key":"32_CR2","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157\u2013166","journal-title":"IEEE Trans Neural Netw"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier W, Weiss B (2005) A\u00a0database of German emotional speech. In: Proc. of interspeech, pp\u00a01517\u20131520. Lisbon, Portugal","DOI":"10.21437\/Interspeech.2005-446"},{"key":"32_CR4","doi-asserted-by":"crossref","unstructured":"Caridakis G, Malatesta L, Kessous L, Amir N, Raouzaiou A, Karpouzis K (2006) Modeling naturalistic affective states via facial and vocal expressions recognition. In: Proc. of the 8th international conference on multimodal interfaces, pp\u00a0146\u2013154. Banff, Alberta, Canada,","DOI":"10.1145\/1180995.1181029"},{"key":"32_CR5","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/978-3-540-85099-1_8","volume-title":"Affect and emotion in human-computer interaction","author":"G Castellano","year":"2008","unstructured":"Castellano G, Kessous L, Caridakis G (2008) Emotion recognition through multiple modalities: face, body gesture, speech. In: Peter\u00a0C, Beale\u00a0R (eds) Affect and emotion in human-computer interaction. Springer, Berlin, pp\u00a092\u2013103"},{"key":"32_CR6","unstructured":"Cowie R, Douglas-Cowie E, Savvidou S, McMahon E, Sawey M, Schr\u00f6der M (2000) Feeltrace: an instrument for recording perceived emotion in real time. In: Proceedings of the ISCA workshop on speech and emotion, pp\u00a019\u201324"},{"key":"32_CR7","unstructured":"Douglas-Cowie E, Cowie R, Sneddon I, Cox C, Lowry O, McRorie M, Martin JC, Devillers L, Abrilian S, Batliner A, Amir N, Karpouzis K (2007) The HUMAINE database. In: Proc. of ACII, pp\u00a0488\u2013500"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2009) openEAR\u2014introducing the Munich Open-source Emotion and Affect Recognition Toolkit. In: Proc. of ACII, pp\u00a0576\u2013581. Amsterdam, The Netherlands","DOI":"10.1109\/ACII.2009.5349350"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"Fernandez S, Graves A, Schmidhuber J (2007) An application of recurrent neural networks to discriminative keyword spotting. In: Proc. of ICANN, pp\u00a0220\u2013229. Porto, Portugal","DOI":"10.1007\/978-3-540-74695-9_23"},{"key":"32_CR10","unstructured":"Fernandez S, Graves A, Schmidhuber J (2008) Phoneme recognition in TIMIT with BLSTM-CTC. Tech. rep., IDSIA"},{"key":"32_CR11","unstructured":"Graves A (2008) Supervised sequence labelling with recurrent neural networks. Ph.D.\u00a0thesis, Technische Universit\u00e4t M\u00fcnchen"},{"issue":"5\u20136","key":"32_CR12","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5\u20136):602\u2013610","journal-title":"Neural Netw"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Graves A, Fernandez S, Schmidhuber J (2005) Bidirectional LSTM networks for improved phoneme classification and recognition. In: Proceedings of ICANN, vol\u00a018. Warsaw, Poland, pp\u00a0602\u2013610","DOI":"10.1007\/11550907_126"},{"key":"32_CR14","unstructured":"Graves A, Fernandez S, Liwicki M, Bunke H, Schmidhuber J (2008) Unconstrained online handwriting recognition with recurrent neural networks. Adv Neural Inf Process Syst"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Grimm M, Kroschel K, Narayanan S (2007) Support vector regression for automatic recognition of spontaneous emotions in speech. In: Proc. of ICASSP, pp\u00a01085\u20131088","DOI":"10.1109\/ICASSP.2007.367262"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Grimm M, Kroschel K, Narayanan S (2008) The vera am mittag german audio-visual emotional speech database. In: Proc. of ICME, pp\u00a0865\u2013868. Hannover, Germany","DOI":"10.1109\/ICME.2008.4607572"},{"issue":"8","key":"32_CR17","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Joachims T (1998) Text categorization with support vector machines: learning with many relevant features. In: Proc. of ECML, pp\u00a0137\u2013142. Chemniz, Germany","DOI":"10.1007\/BFb0026683"},{"issue":"1","key":"32_CR19","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/0893-6080(90)90044-L","volume":"3","author":"KJ Lang","year":"1990","unstructured":"Lang KJ, Waibel AH, Hinton GE (1990) A time-delay neural network architecture for isolated word recognition. Neural Netw 3(1):23\u201343","journal-title":"Neural Netw"},{"issue":"6","key":"32_CR20","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1109\/72.548162","volume":"7","author":"T Lin","year":"1996","unstructured":"Lin T, Horne BG, Tino P, Giles CL (1996) Learning long-term dependencies in NARX recurrent neural networks. IEEE Trans Neural Netw 7(6):1329\u20131338","journal-title":"IEEE Trans Neural Netw"},{"key":"32_CR21","unstructured":"Liwicki M, Graves A, Fernandez S, Bunke H, Schmidhuber J (2007) A\u00a0novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks. In: Proc. of ICDAR, pp\u00a0367\u2013371. Curitiba, Brazil"},{"issue":"4","key":"32_CR22","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1111\/1467-8659.00632","volume":"21","author":"C Peters","year":"2002","unstructured":"Peters C, O\u2019Sullivan C (2002) Synthetic vision and memory for autonomous virtual humans. Comput Graph Forum 21(4):743\u2013753","journal-title":"Comput Graph Forum"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Riedmiller M, Braun H (1993) A\u00a0direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: IEEE international conference on neural networks, pp\u00a0586\u2013591","DOI":"10.1109\/ICNN.1993.298623"},{"issue":"13\u201315","key":"32_CR24","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1016\/j.neucom.2007.12.036","volume":"71","author":"AM Schaefer","year":"2008","unstructured":"Schaefer AM, Udluft S, Zimmermann HG (2008) Learning long-term dependencies with recurrent neural networks. Neurocomputing 71(13\u201315):2481\u20132488","journal-title":"Neurocomputing"},{"issue":"2","key":"32_CR25","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1162\/neco.1992.4.2.234","volume":"4","author":"J Schmidhuber","year":"1992","unstructured":"Schmidhuber J (1992) Learning complex extended sequences using the principle of history compression. Neural Comput 4(2):234\u2013242","journal-title":"Neural Comput"},{"key":"32_CR26","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1007\/978-3-540-74889-2_39","volume-title":"Affective computing and intelligent interaction","author":"M Schr\u00f6der","year":"2007","unstructured":"Schr\u00f6der M, Devillers L, Karpouzis K, Martin JC, Pelachaud C, Peter C, Pirker H, Schuller B, Tao J, Wilson I (2007) What should a generic emotion markup language be able to represent? In: Paiva A, Prada R, Picard RW (eds) Affective computing and intelligent interaction. Springer, Berlin, pp\u00a0440\u2013451"},{"key":"32_CR27","unstructured":"Schr\u00f6der M, Cowie R, Heylen D, Pantic M, Pelachaud C, Schuller B (2008) Towards responsive sensitive artificial listeners. In: Proc. of 4th intern. workshop on human-computer conversation. Bellagio, Italy"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G (2006) Timing levels in segment-based speech emotion recognition. In: Proc. of interspeech, pp\u00a01818\u20131821. Pittsburgh, PA, USA","DOI":"10.21437\/Interspeech.2006-502"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G, Lang M (2003) Hidden Markov model-based speech emotion recognition. In: Proc. of ICASSP, pp\u00a01\u20134. Hong Kong, China","DOI":"10.1109\/ICME.2003.1220939"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Schuller B, Reiter S, Rigoll G (2006) Evolutionary feature generation in speech emotion recognition. In: Proc. of ICME, pp\u00a05\u20138. Toronto, Canada","DOI":"10.1109\/ICME.2006.262500"},{"key":"32_CR31","doi-asserted-by":"crossref","unstructured":"Schuller B, Vlasenko B, Minguez R, Rigoll G, Wendemuth A (2007) Comparing one and two-stage acoustic modeling in the recognition of emotion in speech. In: Proc. of ASRU, pp\u00a0596\u2013600. Kyoto, Japan","DOI":"10.1109\/ASRU.2007.4430180"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Schuller B, Wimmer M, M\u00f6senlechner L, Kern C, Arsic D, Rigoll\u00a0G (2008) Brute-forcing hierarchical functionals for paralinguistics: A\u00a0waste of feature space? In: Proc. of ICASSP, pp\u00a04501\u20134504. Las Vegas, Nevada, USA","DOI":"10.1109\/ICASSP.2008.4518656"},{"issue":"12","key":"32_CR33","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1016\/j.imavis.2009.02.013","volume":"27","author":"B Schuller","year":"2009","unstructured":"Schuller B, M\u00fcller R, Eyben F, Gast J, H\u00f6rnler B, W\u00f6llmer M, Rigoll G, H\u00f6thker A, Konosu H (2009) Being bored? Recognising natural interest by extensive audiovisual integration for real-life application. Image Vis Comput\u00a0J 27(12):1760\u20131774. Special issue on visual and multimodal analysis of human spontaneous behavior","journal-title":"Image Vis Comput\u00a0J"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Schuller B, Steidl S, Batliner A (2009) The Interspeech 2009 emotion challenge. In: Proc. of interspeech, pp\u00a0312\u2013315. Brighton, UK","DOI":"10.21437\/Interspeech.2009-103"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Schuller B, Vlasenko B, Eyben F, Rigoll G, Wendemuth A (2009) Acoustic emotion recognition: A\u00a0benchmark comparison of performances. In: Proc. of ASRU 2009. Merano, Italy","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"32_CR36","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Proc 45:2673\u20132681","journal-title":"IEEE Trans Signal Proc"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Seppi D, Batliner A, Schuller B, Steidl S, Vogt T, Wagner J, Devillers L, Vidrascu L, Amir N, Aharonson V (2008) Patterns, prototypes, performance: classifying emotional user states. In: Proc. of interspeech, pp\u00a0601\u2013604. Brisbane, Australia","DOI":"10.21437\/Interspeech.2008-193"},{"key":"32_CR38","volume-title":"Automatic classification of emotion-related user states in spontaneous children\u2019s speech","author":"S Steidl","year":"2009","unstructured":"Steidl S (2009) Automatic classification of emotion-related user states in spontaneous children\u2019s speech. Logos, Berlin"},{"key":"32_CR39","unstructured":"Steininger S, Schiel F, Dioubina O, Raubold S (2002) Development of user-state conventions for the multimodal corpus in smartkom. In: Workshop on multimodal resources and multimodal systems evaluation, pp\u00a033\u201337. Las Palmas"},{"key":"32_CR40","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/3-540-36678-4_21","volume-title":"SmartKom: foundations of multimodal dialogue systems","author":"M Streit","year":"2006","unstructured":"Streit M, Batliner A, Portele T (2006) Emotions analysis and emotion-handling subdialogues. In: Wahlster W (ed) SmartKom: foundations of multimodal dialogue systems. Springer, Berlin, pp\u00a0317\u2013332"},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Vlasenko B, Schuller B, Wendemuth A, Rigoll G (2007) Frame vs. turn-level: Emotion recognition from speech considering static and dynamic processing. In: Paiva\u00a0A (ed) Proc. of ACII, pp\u00a0139\u2013147. Lisbon, Portugal","DOI":"10.1007\/978-3-540-74889-2_13"},{"key":"32_CR42","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.1109\/5.58337","volume":"78","author":"P Werbos","year":"1990","unstructured":"Werbos P (1990) Backpropagation through time: What it does and how to do it. Proc IEEE 78:1550\u20131560","journal-title":"Proc IEEE"},{"key":"32_CR43","volume-title":"Data Mining: Practical machine learning tools and techniques","author":"IH Witten","year":"2005","unstructured":"Witten IH, Frank E (2005) Data Mining: Practical machine learning tools and techniques, 2nd\u00a0edn. Morgan Kaufmann, San Francisco,","edition":"2"},{"key":"32_CR44","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer M, Eyben F, Reiter S, Schuller B, Cox C, Douglas-Cowie E, Cowie R (2008) Abandoning emotion classes\u2014towards continuous emotion recognition with modelling of long-range dependencies. In: Proc. of interspeech, pp\u00a0597\u2013600. Brisbane, Australia","DOI":"10.21437\/Interspeech.2008-192"},{"key":"32_CR45","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/j.neucom.2009.08.005","volume":"73","author":"M W\u00f6llmer","year":"2009","unstructured":"W\u00f6llmer M, Al-Hames M, Eyben F, Schuller B, Rigoll G (2009) A multidimensional dynamic time warping algorithm for efficient multimodal fusion of asynchronous data streams. Neurocomputing 73:366\u2013380","journal-title":"Neurocomputing"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer M, Eyben F, Keshet J, Graves A, Schuller B, Rigoll G (2009) Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks. In: Proc. of ICASSP, pp\u00a03949\u20133952. Taipei, Taiwan","DOI":"10.1109\/ICASSP.2009.4960492"},{"key":"32_CR47","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer M, Eyben F, Schuller B, Douglas-Cowie E, Cowie R (2009) Data-driven clustering in emotional space for affect recognition using discriminatively trained LSTM networks. In: Proc. of interspeech, pp\u00a01595\u20131598. Brighton, UK","DOI":"10.21437\/Interspeech.2009-474"},{"key":"32_CR48","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer M, Eyben F, Schuller B, Rigoll G (2009) Robust vocabulary independent keyword spotting with graphical models. In: Proc. of ASRU 2009. Merano, Italy","DOI":"10.1109\/ASRU.2009.5373544"},{"key":"32_CR49","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer M, Eyben F, Schuller B, Sun Y, Moosmayr T, Nguyen-Thien N (2009) Robust in-car spelling recognition\u2014a tandem BLSTM-HMM approach. In: Proc. of interspeech, pp\u00a02507\u20132510. Brighton, UK","DOI":"10.21437\/Interspeech.2009-375"},{"issue":"1","key":"32_CR50","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","volume":"31","author":"Z Zeng","year":"2009","unstructured":"Zeng Z, Pantic M, Roisman GI, Huang TS (2009) A survey of affect recognition methods: Audio, visual, and spontaneous expressions. IEEE Trans Pattern Anal Mach Intell 31(1):39\u201358","journal-title":"IEEE Trans Pattern Anal Mach Intell"}],"container-title":["Journal on Multimodal User Interfaces"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-009-0032-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12193-009-0032-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-009-0032-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,27]],"date-time":"2023-05-27T21:32:18Z","timestamp":1685223138000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12193-009-0032-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,12,12]]},"references-count":50,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2010,3]]}},"alternative-id":["32"],"URL":"https:\/\/doi.org\/10.1007\/s12193-009-0032-6","relation":{},"ISSN":["1783-7677","1783-8738"],"issn-type":[{"value":"1783-7677","type":"print"},{"value":"1783-8738","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,12,12]]}}}