{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:51:42Z","timestamp":1740099102314,"version":"3.37.3"},"publisher-location":"Cham","reference-count":22,"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_1","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Gaze, Prosody and Semantics: Relevance of Various Multimodal Signals to Addressee Detection in Human-Human-Computer Conversations"],"prefix":"10.1007","author":[{"given":"Oleg","family":"Akhtiamov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasily","family":"Palkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"key":"1_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-319-64206-2_50","volume-title":"Text, Speech, and Dialogue","author":"A Spirina","year":"2017","unstructured":"Spirina, A., Minker, W., Sidorov, M.: Could emotions be beneficial for interaction quality modelling in human-human conversations? In: Ek\u0161tein, K., Matou\u0161ek, V. (eds.) TSD 2017. LNCS (LNAI), vol. 10415, pp. 447\u2013455. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64206-2_50"},{"issue":"3","key":"1_CR2","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s12193-009-0016-6","volume":"2","author":"A Batliner","year":"2008","unstructured":"Batliner, A., Hacker, C., Noeth, E.: To talk or not to talk with a computer. J. Multimodal User Interfaces 2(3), 171\u2013186 (2008)","journal-title":"J. Multimodal User Interfaces"},{"key":"1_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-40063-X_1","volume-title":"Advances in Multimodal Interfaces \u2014 ICMI 2000","author":"PP Maglio","year":"2000","unstructured":"Maglio, P.P., Matlock, T., Campbell, C.S., Zhai, S., Smith, B.A.: Gaze and speech in attentive user interfaces. In: Tan, T., Shi, Y., Gao, W. (eds.) ICMI 2000. LNCS, vol. 1948, pp. 1\u20137. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-40063-X_1"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Lee, M.K., Kiesler, S., Forlizzi, J.: Receptionist or information kiosk: how do people talk with a robot? In: Proceedings of ACM Conference on Computer-Supported Cooperative Work, pp. 31\u201340 (2010)","DOI":"10.1145\/1718918.1718927"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The INTERSPEECH 2017 computational paralinguistics challenge: addressee, cold & snoring. In: Proceedings of Interspeech, Stockholm (2017)","DOI":"10.21437\/Interspeech.2017-43"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Ouchi, H., Tsuboi, Y.: Addressee and response selection for multi-party conversation. In: Proceedings of EMNLP, Austin, pp. 2133\u20132143 (2016)","DOI":"10.18653\/v1\/D16-1231"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Akhtiamov, O., Sidorov, M., Karpov, A., Minker, W.: Speech and text analysis for multimodal addressee detection in human-human-computer interaction. In: Proceedings of Interspeech, Stockholm, pp. 2521\u20132525 (2017)","DOI":"10.21437\/Interspeech.2017-501"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Ishii, R., Shiro, K., Kazuhiro, O.: Prediction of next-utterance timing using head movement in multi-party meetings. In: Proceedings of the 5th International Conference on Human Agent Interaction. ACM (2017)","DOI":"10.1145\/3125739.3125765"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Skantze, G., Gustafson, J.: Attention and interaction control in a human-human-computer dialogue setting. In: Proceedings of SIGDIAL. Association for Computational Linguistics (2009)","DOI":"10.3115\/1708376.1708421"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Shriberg, E., Stolcke, A., Ravuri, S.: Addressee detection for dialog systems using temporal and spectral dimensions of speaking style. In: Proceedings of Interspeech (2013)","DOI":"10.21437\/Interspeech.2013-576"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Ravuri, S., Stolcke, A.: Recurrent neural network and LSTM models for lexical utterance classification. In: Proceedings of Interspeech, pp. 135\u2013139 (2015)","DOI":"10.1109\/ICASSP.2016.7472844"},{"issue":"9","key":"1_CR12","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/TMM.2015.2454332","volume":"17","author":"TJ Tsai","year":"2015","unstructured":"Tsai, T.J., Stolcke, A., Slaney, M.: A study of multimodal addressee detection in human-human-computer interaction. IEEE Trans. Multimed. 17(9), 1550\u20131561 (2015)","journal-title":"IEEE Trans. Multimed."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Akhtiamov, O., Sergienko, R., Minker, W.: An approach to off-talk detection based on text classification within an automatic spoken dialogue system. In: Proceedings of ICINCO, Lisbon, vol. 2, pp. 288\u2013293 (2016)","DOI":"10.5220\/0005977802880293"},{"key":"1_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1007\/978-3-319-66429-3_14","volume-title":"Speech and Computer","author":"O Akhtiamov","year":"2017","unstructured":"Akhtiamov, O., Ubskii, D., Feldina, E., Pugachev, A., Karpov, A., Minker, W.: Are you addressing me? Multimodal addressee detection in human-human-computer conversations. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 152\u2013161. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_14"},{"key":"1_CR15","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-319-71746-3_4","volume-title":"Artificial Intelligence and Natural Language","author":"A Pugachev","year":"2018","unstructured":"Pugachev, A., Akhtiamov, O., Karpov, A., Minker, W.: Deep learning for acoustic addressee detection in spoken dialogue systems. In: Filchenkov, A., Pivovarova, L., \u017di\u017eka, J. (eds.) AINL 2017. CCIS, vol. 789, pp. 45\u201353. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-71746-3_4"},{"issue":"2","key":"1_CR16","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola, P., Jones, M.: Robust real-time face detection. Int. J. Comput. Vis. 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. In: Proceedings of Interspeech, Lyon (2013)","DOI":"10.21437\/Interspeech.2013-56"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Schuller, B., et al: The INTERSPEECH 2016 computational paralinguistics challenge: deception, sincerity & native language. In: Proceedings of Interspeech (2016)","DOI":"10.21437\/Interspeech.2016-129"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of EMNLP, Doha, vol. 14, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"issue":"8","key":"1_CR20","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. J. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"J. Neural Comput."},{"issue":"1","key":"1_CR21","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. ML Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. ML Res."},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Noth, E., Hacker, C., Batliner, A.: Does multimodality really help? The classification of emotion and of on\/off-focus in multimodal dialogues. In:\u00a0ELMAR. IEEE (2007)","DOI":"10.1109\/ELMAR.2007.4418790"}],"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_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T04:50:45Z","timestamp":1661835045000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}