{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:33:19Z","timestamp":1750221199189,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,10,2]],"date-time":"2018-10-02T00:00:00Z","timestamp":1538438400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["107-2634-F-007 -006 -"],"award-info":[{"award-number":["107-2634-F-007 -006 -"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,10,2]]},"DOI":"10.1145\/3242969.3242992","type":"proceedings-article","created":{"date-parts":[[2018,10,2]],"date-time":"2018-10-02T12:09:29Z","timestamp":1538482169000},"page":"55-62","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Generating fMRI-Enriched Acoustic Vectors using a Cross-Modality Adversarial Network for Emotion Recognition"],"prefix":"10.1145","author":[{"given":"Gao-Yi","family":"Chao","sequence":"first","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu, Taiwan Roc"}]},{"given":"Chun-Min","family":"Chang","sequence":"additional","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu, Taiwan Roc"}]},{"given":"Jeng-Lin","family":"Li","sequence":"additional","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu, Taiwan Roc"}]},{"given":"Ya-Tse","family":"Wu","sequence":"additional","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu, Taiwan Roc"}]},{"given":"Chi-Chun","family":"Lee","sequence":"additional","affiliation":[{"name":"National Tsing Hua University & MOST Joint Research Center for AI Technology and All Vista Healthcare, Hsinchu, Taiwan Roc"}]}],"member":"320","published-online":{"date-parts":[[2018,10,2]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178934"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Matthew Black Athanasios Katsamanis Chi-Chun Lee Adam C Lammert Brian R Baucom Andrew Christensen Panayiotis G Georgiou and Shrikanth S Narayanan . 2010. Automatic classification of married couples' behavior using audio features Eleventh Annual Conference of the International Speech Communication Association.  Matthew Black Athanasios Katsamanis Chi-Chun Lee Adam C Lammert Brian R Baucom Andrew Christensen Panayiotis G Georgiou and Shrikanth S Narayanan . 2010. Automatic classification of married couples' behavior using audio features Eleventh Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2010-574"},{"key":"e_1_3_2_1_3_1","unstructured":"P Boersma and D Weenink . 2001. Praat speech processing software. Institute of Phonetics Sciences of the University of Amsterdam. http:\/\/www. praat. org (2001).  P Boersma and D Weenink . 2001. Praat speech processing software. Institute of Phonetics Sciences of the University of Amsterdam. http:\/\/www. praat. org (2001)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0926-6410(99)00060-9"},{"volume-title":"IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation","year":"2008","author":"Busso Carlos","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027968"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITCS.2009.108"},{"volume-title":"Adversarial Image Synthesis for Unpaired Multi-modal Cardiac Data International Workshop on Simulation and Synthesis in Medical Imaging. Springer, 3--13","year":"2017","author":"Chartsias Agisilaos","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472784"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICICS.1997.647126"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"George H Dunteman . 1989. Principal components analysis. Number 69. Sage.  George H Dunteman . 1989. Principal components analysis. Number 69. Sage.","DOI":"10.4135\/9781412985475"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.04.054"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Daniel Joseph France Richard G Shiavi Stephen Silverman Marilyn Silverman and M Wilkes . 2000. Acoustical properties of speech as indicators of depression and suicidal risk. IEEE transactions on Biomedical Engineering Vol. 47 7 (2000) 829--837.  Daniel Joseph France Richard G Shiavi Stephen Silverman Marilyn Silverman and M Wilkes . 2000. Acoustical properties of speech as indicators of depression and suicidal risk. IEEE transactions on Biomedical Engineering Vol. 47 7 (2000) 829--837.","DOI":"10.1109\/10.846676"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Sascha Fr\u00fchholz Wiebke Trost and Didier Grandjean . 2014. The role of the medial temporal limbic system in processing emotions in voice and music. Progress in neurobiology Vol. 123 (2014) 1--17.  Sascha Fr\u00fchholz Wiebke Trost and Didier Grandjean . 2014. The role of the medial temporal limbic system in processing emotions in voice and music. Progress in neurobiology Vol. 123 (2014) 1--17.","DOI":"10.1016\/j.pneurobio.2014.09.003"},{"key":"e_1_3_2_1_15_1","unstructured":"Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio . 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.   Ian Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio . 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Didier Grandjean David Sander Gilles Pourtois Sophie Schwartz Mohamed L Seghier Klaus R Scherer and Patrik Vuilleumier . 2005. The voices of wrath: brain responses to angry prosody in meaningless speech. Nature neuroscience Vol. 8 2 (2005) 145.  Didier Grandjean David Sander Gilles Pourtois Sophie Schwartz Mohamed L Seghier Klaus R Scherer and Patrik Vuilleumier . 2005. The voices of wrath: brain responses to angry prosody in meaningless speech. Nature neuroscience Vol. 8 2 (2005) 145.","DOI":"10.1038\/nn1392"},{"key":"e_1_3_2_1_17_1","unstructured":"Ishaan Gulrajani Faruk Ahmed Martin Arjovsky Vincent Dumoulin and Aaron C Courville . 2017. Improved training of wasserstein gans. In Advances in Neural Information Processing Systems. 5769--5779.  Ishaan Gulrajani Faruk Ahmed Martin Arjovsky Vincent Dumoulin and Aaron C Courville . 2017. Improved training of wasserstein gans. In Advances in Neural Information Processing Systems. 5769--5779."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Kun Han Dong Yu and Ivan Tashev . 2014. Speech emotion recognition using deep neural network and extreme learning machine Fifteenth Annual Conference of the International Speech Communication Association.  Kun Han Dong Yu and Ivan Tashev . 2014. Speech emotion recognition using deep neural network and extreme learning machine Fifteenth Annual Conference of the International Speech Communication Association.","DOI":"10.21437\/Interspeech.2014-57"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462352"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1093\/scan\/nsl027"},{"volume-title":"In-vehicle corpus and signal processing for driver behavior","author":"Li Ma","key":"e_1_3_2_1_21_1"},{"key":"e_1_3_2_1_22_1","unstructured":"Josh Merel Yuval Tassa Sriram Srinivasan Jay Lemmon Ziyu Wang Greg Wayne and Nicolas Heess . 2017. Learning human behaviors from motion capture by adversarial imitation. arXiv preprint arXiv:1707.02201 (2017).  Josh Merel Yuval Tassa Sriram Srinivasan Jay Lemmon Ziyu Wang Greg Wayne and Nicolas Heess . 2017. Learning human behaviors from motion capture by adversarial imitation. arXiv preprint arXiv:1707.02201 (2017)."},{"key":"e_1_3_2_1_23_1","unstructured":"Wolfgang Minker and Samir Bennacef . 2004. Speech and human-machine dialog. Vol. Vol. 770. Springer Science & Business Media.  Wolfgang Minker and Samir Bennacef . 2004. Speech and human-machine dialog. Vol. Vol. 770. Springer Science & Business Media."},{"key":"e_1_3_2_1_24_1","unstructured":"Mehdi Mirza and Simon Osindero . 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014).  Mehdi Mirza and Simon Osindero . 2014. Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.0006-341X.1999.00463.x"},{"key":"e_1_3_2_1_26_1","unstructured":"Valery Petrushin . 1999. Emotion in speech: Recognition and application to call centers Proceedings of Artificial Neural Networks in Engineering Vol. Vol. 710.  Valery Petrushin . 1999. Emotion in speech: Recognition and application to call centers Proceedings of Artificial Neural Networks in Engineering Vol. Vol. 710."},{"key":"e_1_3_2_1_27_1","unstructured":"Tran Minh Quan Thanh Nguyen-Duc and Won-Ki Jeong . 2018. Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss. IEEE Transactions on Medical Imaging (2018).  Tran Minh Quan Thanh Nguyen-Duc and Won-Ki Jeong . 2018. Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss. IEEE Transactions on Medical Imaging (2018)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEEC.2014.6958552"},{"key":"e_1_3_2_1_30_1","unstructured":"Samarth Tripathi and Homayoon Beigi . 2018. Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning. arXiv preprint arXiv:1804.05788 (2018).  Samarth Tripathi and Homayoon Beigi . 2018. Multi-Modal Emotion recognition on IEMOCAP Dataset using Deep Learning. arXiv preprint arXiv:1804.05788 (2018)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0978"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3143011"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-646"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-562"},{"key":"e_1_3_2_1_35_1","unstructured":"Chaogan Yan and Yufeng Zang . 2010. DPARSF: a MATLAB toolbox for\" pipeline\" data analysis of resting-state fMRI. Frontiers in systems neuroscience Vol. 4 (2010) 13.  Chaogan Yan and Yufeng Zang . 2010. DPARSF: a MATLAB toolbox for\" pipeline\" data analysis of resting-state fMRI. Frontiers in systems neuroscience Vol. 4 (2010) 13."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997630"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.52"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"Tinghui Zhou Philipp Krahenbuhl Mathieu Aubry Qixing Huang and Alexei A Efros . 2016. Learning dense correspondence via 3d-guided cycle consistency Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 117--126.  Tinghui Zhou Philipp Krahenbuhl Mathieu Aubry Qixing Huang and Alexei A Efros . 2016. Learning dense correspondence via 3d-guided cycle consistency Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 117--126.","DOI":"10.1109\/CVPR.2016.20"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39065-4_6"}],"event":{"name":"ICMI '18: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","sponsor":["SIGCHI Specialist Interest Group in Computer-Human Interaction of the ACM"],"location":"Boulder CO USA","acronym":"ICMI '18"},"container-title":["Proceedings of the 20th ACM International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3242969.3242992","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3242969.3242992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:25Z","timestamp":1750210765000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3242969.3242992"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,2]]},"references-count":39,"alternative-id":["10.1145\/3242969.3242992","10.1145\/3242969"],"URL":"https:\/\/doi.org\/10.1145\/3242969.3242992","relation":{},"subject":[],"published":{"date-parts":[[2018,10,2]]},"assertion":[{"value":"2018-10-02","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}