{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T17:17:31Z","timestamp":1721841451484},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,7,30]],"date-time":"2013-07-30T00:00:00Z","timestamp":1375142400000},"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":[[2014,3]]},"DOI":"10.1007\/s12193-013-0128-x","type":"journal-article","created":{"date-parts":[[2013,7,29]],"date-time":"2013-07-29T10:27:39Z","timestamp":1375093659000},"page":"87-96","source":"Crossref","is-referenced-by-count":7,"title":["Facial expression-based affective speech translation"],"prefix":"10.1007","volume":"8","author":[{"given":"\u00c9va","family":"Sz\u00e9kely","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ingmar","family":"Steiner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeeshan","family":"Ahmed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julie","family":"Carson-Berndsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,7,30]]},"reference":[{"key":"128_CR1","doi-asserted-by":"crossref","unstructured":"Ag\u00fcero PD, Adell J, Bonafonte A (2006) Prosody generation for speech-to-speech translation. In: IEEE international conference on acoustics, speech, and signal processing, pp I-557\u2013I-560. doi: 10.1109\/ICASSP.2006.1660081","DOI":"10.1109\/ICASSP.2006.1660081"},{"key":"128_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed Z, Steiner I, Sz\u00e9kely \u00c9, Carson-Berndsen J (2013) A system for facial expression-based affective speech translation. In: ACM international conference on intelligent user interfaces companion, pp 57\u201358. doi: 10.1145\/2451176.2451197","DOI":"10.1145\/2451176.2451197"},{"key":"128_CR3","doi-asserted-by":"crossref","unstructured":"Batliner A, Huber R, Niemann H, N\u00f6th E, Spilker J, Fischer K (2000) The recognition of emotion. In: Wahlster W (ed) Verbmobil: foundations of speech-to-speech translations. Springer, Berlin, pp 122\u2013130","DOI":"10.1007\/978-3-662-04230-4_9"},{"key":"128_CR4","volume-title":"Classification and regression trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth, Belmont"},{"issue":"3","key":"128_CR5","doi-asserted-by":"crossref","first-page":"27:1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: A library for support vector machines. ACM Trans Intell Syst Technol 2(3):27:1\u201327:27. doi: 10.1145\/1961189.1961199","journal-title":"ACM Trans Intell Syst Technol"},{"key":"128_CR6","unstructured":"Cowie R, Douglas-Cowie E, Apolloni B, Taylor JG, Romano A, Fellenz W (1999) What a neural net needs to know about emotion words. In: World multiconference on circuits, systems, communications and computer, pp 109\u2013114"},{"issue":"1","key":"128_CR7","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie R, Douglas-Cowie E, Tsapatsoulis N, Votsis G, Kollias S, Fellenz W, Taylor JG (2001) Emotion recognition in human\u2013computer interaction. IEEE Signal Process Mag 18(1):32\u201380. doi: 10.1109\/79.911197","journal-title":"IEEE Signal Process Mag"},{"key":"128_CR8","first-page":"27","volume-title":"Nonverbal communication: where nature meets culture","author":"P Ekman","year":"1997","unstructured":"Ekman P, Keltner D (1997) Universal facial expressions of emotion: an old controversy and new findings. In: Segerstr\u00e5le U, Moln\u00e1r P (eds) Nonverbal communication: where nature meets culture. Lawrence Erlbaum, New Jersey, pp 27\u201346"},{"key":"128_CR9","unstructured":"Kano T, Sakti S, Takamichi S, Neubig G, Toda T, Nakamura S (2012) A method for translation of paralinguistic information. In: International workshop on spoken language translation"},{"key":"128_CR10","doi-asserted-by":"crossref","unstructured":"K\u00fcblbeck C, Ernst A (2006) Face detection and tracking in video sequences using the modified census transformation. Image Vis Comput 24(6):564\u2013572. doi: 10.1016\/j.imavis.2005.08.005","DOI":"10.1016\/j.imavis.2005.08.005"},{"key":"128_CR11","doi-asserted-by":"crossref","unstructured":"Machado AF, Queiroz M (2010) Techniques for crosslingual voice conversion. In: IEEE International symposium on multimedia, pp 365\u2013370. doi: 10.1109\/ISM.2010.62","DOI":"10.1109\/ISM.2010.62"},{"key":"128_CR12","doi-asserted-by":"crossref","unstructured":"McKeown G, Valstar MF, Cowie R, Pantic M (2010) The SEMAINE corpus of emotionally coloured character interactions. In: IEEE international conference on multimedia and expo, pp 1079\u20131084. doi: 10.1109\/ICME.2010.5583006","DOI":"10.1109\/ICME.2010.5583006"},{"key":"128_CR13","doi-asserted-by":"crossref","unstructured":"Och FJ (2003) Minimum error rate training in statistical machine translation. In: Annual meeting of the association for computational linguistics, pp 160\u2013167. doi: 10.3115\/1075096.1075117","DOI":"10.3115\/1075096.1075117"},{"key":"128_CR14","doi-asserted-by":"crossref","unstructured":"Schr\u00f6der M, Baggia P, Burkhardt F, Pelachaud C, Peter C, Zovato E (2011) EmotionML\u2014an upcoming standard for representing emotions and related states. In: D\u2019Mello S, Graesser A, Schuller B, Martin JC (eds) Affective computing and intelligent interaction. Springer, Berlin, pp 316\u2013325. doi: 10.1007\/978-3-642-24600-5_35","DOI":"10.1007\/978-3-642-24600-5_35"},{"issue":"4","key":"128_CR15","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1023\/A:1025708916924","volume":"6","author":"M Schr\u00f6der","year":"2003","unstructured":"Schr\u00f6der M, Trouvain J (2003) The German text-to-speech synthesis system MARY: a tool for research, development and teaching. Int J Speech Technol 6(4):365\u2013377. doi: 10.1023\/A:1025708916924","journal-title":"Int J Speech Technol"},{"key":"128_CR16","doi-asserted-by":"crossref","unstructured":"Shin J, Georgiou PG, Narayanan S (2013) Enabling effective design of multimodal interfaces for speech-to-speech translation system: an empirical study of longitudinal user behaviors over time and user strategies for coping with errors. Comput. Speech Lang 27(2):554\u2013571. doi: 10.1016\/j.csl.2012.02.001","DOI":"10.1016\/j.csl.2012.02.001"},{"key":"128_CR17","unstructured":"Steiner I, Schr\u00f6der M, Charfuelan M, Klepp A (2010) Symbolic vs. acoustics-based style control for expressive unit selection. In: ISCA workshop on speech Synthesis, pp 114\u2013119"},{"key":"128_CR18","unstructured":"Sz\u00e9kely \u00c9, Ahmed Z, Cabral JP, Carson-Berndsen J (2012) WinkTalk: a demonstration of a multimodal speech synthesis platform linking facial expressions to expressive synthetic voices. In: Workshop on speech and language processing for assistive technologies, pp 5\u20138"},{"key":"128_CR19","doi-asserted-by":"crossref","unstructured":"Tom\u00e1s J, Canovas A, Lloret J, Garc\u00eda M (2010) Speech translation statistical system using multimodal sources of knowledge. In: International multi-conference on computing in the global information technology, pp 5\u20139. doi: 10.1109\/ICCGI.2010.26","DOI":"10.1109\/ICCGI.2010.26"},{"key":"128_CR20","doi-asserted-by":"crossref","first-page":"333","DOI":"10.7551\/mitpress\/5779.003.0035","volume-title":"Readings in machine translation, chap. 28","author":"B Vauquois","year":"2003","unstructured":"Vauquois B (2003) Automatic translation\u2014a survey of different approaches. In: Nirenburg S, Somers HL, Wilks Y (eds) Readings in machine translation, chap. 28. MIT Press, Cambridge, pp 333\u2013338"},{"key":"128_CR21","doi-asserted-by":"crossref","unstructured":"W\u00f6llmer M, Metallinou A, Eyben F, Schuller B, Narayanan S (2010) Context-sensitive multimodal emotion recognition from speech and facial expression using bidirectional LSTM modeling. In: Interspeech, pp 2362\u20132365","DOI":"10.21437\/Interspeech.2010-646"}],"container-title":["Journal on Multimodal User Interfaces"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0128-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12193-013-0128-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12193-013-0128-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,15]],"date-time":"2024-05-15T14:45:55Z","timestamp":1715784355000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12193-013-0128-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7,30]]},"references-count":21,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,3]]}},"alternative-id":["128"],"URL":"https:\/\/doi.org\/10.1007\/s12193-013-0128-x","relation":{},"ISSN":["1783-7677","1783-8738"],"issn-type":[{"value":"1783-7677","type":"print"},{"value":"1783-8738","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,7,30]]}}}