{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T19:06:01Z","timestamp":1742929561177,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984343"},{"type":"electronic","value":"9789819984350"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8435-0_13","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"164-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pairwise-Emotion Data Distribution Smoothing for\u00a0Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Hexin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefeng","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Ando, A., Kobashikawa, S., Kamiyama, H., Masumura, R., Ijima, Y., Aono, Y.: Soft-target training with ambiguous emotional utterances for DNN-based speech emotion classification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4964\u20134968 (2018)","DOI":"10.1109\/ICASSP.2018.8461299"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Ando, A., Masumura, R., Kamiyama, H., Kobashikawa, S., Aono, Y.: Speech emotion recognition based on multi-label emotion existence model. In: Proc. Interspeech 2019, pp. 2818\u20132822 (2019)","DOI":"10.21437\/Interspeech.2019-2524"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Atmaja, B.T., Shirai, K., Akagi, M.: Speech emotion recognition using speech feature and word embedding. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 519\u2013523 (2019)","DOI":"10.1109\/APSIPAASC47483.2019.9023098"},{"key":"13_CR4","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: data2vec: A general framework for self-supervised learning in speech, vision and language. In: Proceedings of the 39th International Conference on Machine Learning. vol. 162, pp. 1298\u20131312 (2022)"},{"key":"13_CR5","unstructured":"Batliner, A., Steidl, S., N\u00f6th, E.: Releasing a thoroughly annotated and processed spontaneous emotional database: the FAU Aibo emotion corpus. In: Proc. Workshop Lang. Resour. Eval. Conf. vol. 28, pp. 28\u201331 (2008)"},{"issue":"4","key":"13_CR6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: IEMOCAP: Interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Chou, H.C., Lin, W.C., Lee, C.C., Busso, C.: Exploiting annotators\u2019 typed description of emotion perception to maximize utilization of ratings for speech emotion recognition. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7717\u20137721 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746990"},{"issue":"1","key":"13_CR8","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie, R., et al.: Emotion recognition in human-computer interaction. IEEE Signal Process. Mag. 18(1), 32\u201380 (2001)","journal-title":"IEEE Signal Process. Mag."},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Delbrouck, J.B., Tits, N., Dupont, S.: Modulated fusion using transformer for linguistic-acoustic emotion recognition. In: Proceedings of the First International Workshop on Natural Language Processing Beyond Text, pp. 1\u201310 (2020)","DOI":"10.18653\/v1\/2020.nlpbt-1.1"},{"key":"13_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. vol. 1, pp. 4171\u20134186 (2019)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Fayek, H.M., Lech, M., Cavedon, L.: Modeling subjectiveness in emotion recognition with deep neural networks: Ensembles vs soft labels. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 566\u2013570 (2016)","DOI":"10.1109\/IJCNN.2016.7727250"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Fujioka, T., Homma, T., Nagamatsu, K.: Meta-learning for speech emotion recognition considering ambiguity of emotion labels. In: Proc. Interspeech 2020, pp. 2332\u20132336 (2020)","DOI":"10.21437\/Interspeech.2020-1082"},{"key":"13_CR13","doi-asserted-by":"crossref","unstructured":"Gao, X., Zhao, Y., Zhang, J., Cai, L.: Pairwise emotional relationship recognition in drama videos: Dataset and benchmark. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3380\u20133389 (2021)","DOI":"10.1145\/3474085.3475493"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"Gupta, P., Rajput, N.: Two-stream emotion recognition for call center monitoring. In: Proc. Interspeech 2007, pp. 2241\u20132244 (2007)","DOI":"10.21437\/Interspeech.2007-609"},{"key":"13_CR15","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Poria, S., Mihalcea, R., Cambria, E., Zimmermann, R.: ICON: Interactive conversational memory network for multimodal emotion detection. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2594\u20132604 (2018)","DOI":"10.18653\/v1\/D18-1280"},{"key":"13_CR16","doi-asserted-by":"crossref","unstructured":"Huahu, X., Jue, G., Jian, Y.: Application of speech emotion recognition in intelligent household robot. In: 2010 International Conference on Artificial Intelligence and Computational Intelligence. vol. 1, pp. 537\u2013541 (2010)","DOI":"10.1109\/AICI.2010.118"},{"issue":"7","key":"13_CR17","first-page":"8419","volume":"45","author":"Z Lian","year":"2023","unstructured":"Lian, Z., Chen, L., Sun, L., Liu, B., Tao, J.: GCNet: Graph completion network for incomplete multimodal learning in conversation. IEEE Trans. Pattern Anal. Mach. Intell. 45(7), 8419\u20138432 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"13_CR18","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TASLP.2021.3049898","volume":"29","author":"Z Lian","year":"2021","unstructured":"Lian, Z., Liu, B., Tao, J.: CTNet: Conversational transformer network for emotion recognition. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 29, 985\u20131000 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Lotfian, R., Busso, C.: Predicting categorical emotions by jointly learning primary and secondary emotions through multitask learning. In: Proc. Interspeech 2018, pp. 951\u2013955 (2018)","DOI":"10.21437\/Interspeech.2018-2464"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"Parry, J., Palaz, D., et al: Analysis of Deep Learning Architectures for Cross-Corpus Speech Emotion Recognition. In: Proc. Interspeech 2019, pp. 1656\u20131660 (2019)","DOI":"10.21437\/Interspeech.2019-2753"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Hazarika, D., Majumder, N., Zadeh, A., Morency, L.P.: Context-dependent sentiment analysis in user-generated videos. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. vol. 1, pp. 873\u2013883 (2017)","DOI":"10.18653\/v1\/P17-1081"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Seppi, D., et al: Patterns, prototypes, performance: classifying emotional user states. In: Proc. Interspeech 2008, pp. 601\u2013604 (2008)","DOI":"10.21437\/Interspeech.2008-193"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Sun, L., Liu, B., Tao, J., Lian, Z.: Multimodal cross-and self-attention network for speech emotion recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 4275\u20134279 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Yin, Y., Gu, Y., Yao, L., Zhou, Y., Liang, X., Zhang, H.: Progressive co-teaching for ambiguous speech emotion recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6264\u20136268 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414494"},{"key":"13_CR25","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. In: International Conference on Learning Representations (2018)"},{"key":"13_CR26","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1109\/TASLP.2022.3145287","volume":"30","author":"Y Zhou","year":"2022","unstructured":"Zhou, Y., Liang, X., Gu, Y., Yin, Y., Yao, L.: Multi-classifier interactive learning for ambiguous speech emotion recognition. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 30, 695\u2013705 (2022)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Zou, H., Si, Y., Chen, C., Rajan, D., Chng, E.S.: Speech emotion recognition with co-attention based multi-level acoustic information. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 7367\u20137371 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747095"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8435-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:11:58Z","timestamp":1703319118000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8435-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984343","9789819984350"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8435-0_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}