{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T10:18:17Z","timestamp":1778149097803,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819706686","type":"print"},{"value":"9789819706693","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-0669-3_6","type":"book-chapter","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T21:20:16Z","timestamp":1709155216000},"page":"63-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-scale Aggregation Network for\u00a0Speech Emotion Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2518-7180","authenticated-orcid":false,"given":"An","family":"Dang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4719-2014","authenticated-orcid":false,"given":"Ha My","family":"Linh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5458-3713","authenticated-orcid":false,"given":"Duc-Quang","family":"Vu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,29]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Huang, Z., Epps, J., Joachim, D.: Speech landmark bigrams for depression detection from naturalistic smartphone speech. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5856\u20135860 (2019)","DOI":"10.1109\/ICASSP.2019.8682916"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Anttonen, J., Surakka, V.: Emotions and heart rate while sitting on a chair. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, ACM, pp. 491\u2013499 (2005)","DOI":"10.1145\/1054972.1055040"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Vogel, H.J., et al.: Emotional awareness for intelligent vehicle assistants: a research agenda. In: IEEE\/ACM 1st International Workshop on Software Engineering for AI in Autonomous Systems (SEFAIAS), pp. 11\u201315 (2018)","DOI":"10.1145\/3194085.3194094"},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"2105","DOI":"10.1109\/TCSVT.2015.2444731","volume":"25","author":"MS Hossain","year":"2015","unstructured":"Hossain, M.S., Muhammad, G., Song, B., Hassan, M.M., Alelaiwi, A., Alamri, A.: Audio-visual emotion-aware cloud gaming framework. IEEE Trans. Circ. Syst. Video Technol. 25, 2105\u20132118 (2015)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"6_CR5","doi-asserted-by":"publisher","unstructured":"Badshah, A.M., Ahmad, J., Rahim, N., Baik, S.W.: Speech emotion recognition from spectrograms with deep convolutional neural network. In: 2017 International Conference on Platform Technology and Service (PlatCon) (Busan), pp. 1\u20135 (2017). https:\/\/doi.org\/10.1109\/PlatCon","DOI":"10.1109\/PlatCon"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Anvarjon, T., Kwon, S.: Deep-Net: a lightweight CNN-based speech emotion recognition system using deep frequency features. Sensors, 5212 (2020)","DOI":"10.3390\/s20185212"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Kurpukdee, N., Koriyama, T., Kobayashi, T., Kasuriya, S., Wutiwiwatchai, C., Lamsrichan, P.: Speech emotion recognition using convolutional long short-term memory neural network and support vector machines. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1744\u20131749 (2017)","DOI":"10.1109\/APSIPA.2017.8282315"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Satt, A., Rozenberg, S., Hoory, R.: Efficient emotion recognition from speech using deep learning on spectrograms. In: Proceedings of the INTERSPEECH, pp. 1089\u20131093 (2017)","DOI":"10.21437\/Interspeech.2017-200"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Etienne, C., Fidanza, G., Petrovskii, A., Devillers, L., Schmauch, B.: CNN+ LSTM architecture for speech emotion recognition with data augmentation. arXiv preprint arXiv:1802.05630 (2018)","DOI":"10.21437\/SMM.2018-5"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Pappagari, R., Wang, T., Villalba, J., Chen, N., Dehak, N.: X-vectors meet emotions: a study on dependencies between emotion and speaker recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7169\u20137173 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Lakomkin, E., Zamani, M.A., Weber, C., Magg, S., Wermter, S.: On the robustness of speech emotion recognition for human-robot interaction with deep neural networks. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, pp. 854\u2013860 (2018)","DOI":"10.1109\/IROS.2018.8593571"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 936\u2013944 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"6_CR13","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2999\u20133007 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"6_CR15","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. ArXiv abs\/1704.04861 (2017)"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Nediyanchath, A., Paramasivam, P., Yenigalla, P.: Multi-head attention for speech emotion recognition with auxiliary learning of gender recognition. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2020)","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Keren, G., Schuller, B.: Convolutional RNN: an enhanced model for extracting features from sequential data. In: Proceedings of the IEEE IJCNN, pp. 3412\u20133419 (2016)","DOI":"10.1109\/IJCNN.2016.7727636"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Xie, Y., Liang, R., Liang, Z., Zhao, L.: Attention-based dense LSTM for speech emotion recognition. In: IEICE Trans. Inf. Syst. 1426\u20131429 (2019)","DOI":"10.1587\/transinf.2019EDL8019"},{"key":"6_CR19","unstructured":"Ma, X., Wu, Z., Jia, J., Xu, M., Meng, H., Cai, L.: INTERSPEECH, pp. 3683\u20133687 (2018)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Chen, M., He, X., Yang, J., Zhang, H.: 3-D convolutional recurrent neural networks with attention model for speech emotion recognition. IEEE Signal Process. Lett. 1440\u20131444 (2018)","DOI":"10.1109\/LSP.2018.2860246"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Tashev, I.: High-level feature representation using recurrent neural network for speech emotion recognition. In: INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-336"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Peng, Z., Lu, Y., Pan, S., Liu, Y.: Efficient speech emotion recognition using multi-scale CNN and attention. In: ICASSP (2021)","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Vu, T.H., Dang, A., Wang, J.C.: Learning to remember beauty products. In: Proceedings of the 28th ACM International Conference on Multimedia (2020)","DOI":"10.1145\/3394171.3416281"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Dang, A., Vu, T.H., Wang, J.C.: EMIX: a data augmentation method for speech emotion recognition. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096789"}],"container-title":["Lecture Notes in Computer Science","Computational Data and Social Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0669-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T21:21:50Z","timestamp":1709155310000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0669-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819706686","9789819706693"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0669-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CSoNet","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Data and Social Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"11 December 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"csonet2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/csonet-conf.github.io\/csonet23\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"64","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":"23","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":"14","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":"36% - 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":"2.7","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":"2.0","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The four extended abstracts are also included in this proceedings.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}