{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:13:51Z","timestamp":1776888831579,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819981373","type":"print"},{"value":"9789819981380","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,26]],"date-time":"2023-11-26T00:00:00Z","timestamp":1700956800000},"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\/978-981-99-8138-0_33","type":"book-chapter","created":{"date-parts":[[2023,11,25]],"date-time":"2023-11-25T10:02:23Z","timestamp":1700906543000},"page":"415-427","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Time-Frequency Transformer: A Novel Time Frequency Joint Learning Method for\u00a0Speech Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Yong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Zong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hailun","family":"Lian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,26]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Schuller, B., Batliner, A.: Computational Paralinguistics: Emotion, Affect and Personality in Speech and Language Processing. John Wiley & Sons (2013)","DOI":"10.1002\/9781118706664"},{"issue":"5","key":"33_CR2","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1145\/3129340","volume":"61","author":"BW Schuller","year":"2018","unstructured":"Schuller, B.W.: Speech emotion recognition: two decades in a nutshell, benchmarks, and ongoing trends. Commun. ACM 61(5), 90\u201399 (2018)","journal-title":"Commun. ACM"},{"key":"33_CR3","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","volume":"116","author":"MB Ak\u00e7ay","year":"2020","unstructured":"Ak\u00e7ay, M.B., O\u011fuz, K.: Speech emotion recognition: emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Commun. 116, 56\u201376 (2020)","journal-title":"Speech Commun."},{"key":"33_CR4","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/TASLP.2022.3178232","volume":"30","author":"C Lu","year":"2022","unstructured":"Lu, C., Zong, Y., Zheng, W., Li, Y., Tang, C., Schuller, B.W.: Domain invariant feature learning for speaker-independent speech emotion recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 2217\u20132230 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Stuhlsatz, A., Meyer, C., Eyben, F., Zielke, T., Meier, G., Schuller, B.: Deep neural networks for acoustic emotion recognition: raising the benchmarks. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5688\u20135691. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5947651"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Schuller, B., Vlasenko, B., Eyben, F., Rigoll, G., Wendemuth, A.: Acoustic emotion recognition: a benchmark comparison of performances. In: 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, pp. 552\u2013557. IEEE (2009)","DOI":"10.1109\/ASRU.2009.5372886"},{"issue":"4","key":"33_CR7","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.3390\/s21041249","volume":"21","author":"BJ Abbaschian","year":"2021","unstructured":"Abbaschian, B.J., Sierra-Sosa, D., Elmaghraby, A.: Deep learning techniques for speech emotion recognition, from databases to models. Sensors 21(4), 1249 (2021)","journal-title":"Sensors"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Wang, J., Xue, M., Culhane, R., Diao, E., Ding, J., Tarokh, V.: Speech emotion recognition with dual-sequence LSTM architecture. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), pp. 6474\u20136478. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054629"},{"issue":"8","key":"33_CR9","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1109\/TMM.2014.2360798","volume":"16","author":"Q Mao","year":"2014","unstructured":"Mao, Q., Dong, M., Huang, Z., Zhan, Y.: Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans. Multimedia 16(8), 2203\u20132213 (2014)","journal-title":"IEEE Trans. Multimedia"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Lu, C., et al.: Speech emotion recognition via an attentive time\u2013frequency neural network. IEEE Trans. Computat. Soc. Syst. (2022)","DOI":"10.1109\/TCSS.2022.3219825"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"Satt, A., et al.: Efficient emotion recognition from speech using deep learning on spectrograms. In: Interspeech, pp. 1089\u20131093 (2017)","DOI":"10.21437\/Interspeech.2017-200"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Wu, X., et al.: Speech emotion recognition using capsule networks. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6695\u20136699. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Dubey, S.R., Singh, S.K., Chaudhuri, B.B.: Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing (2022)","DOI":"10.1016\/j.neucom.2022.06.111"},{"key":"33_CR14","unstructured":"Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Busso, C., et al.: Iemocap: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","DOI":"10.1007\/s10579-008-9076-6"},{"key":"33_CR16","unstructured":"Zhang, J., Jia, H.: Design of speech corpus for mandarin text to speech. In: The Blizzard Challenge 2008 Workshop (2008)"},{"key":"33_CR17","doi-asserted-by":"crossref","unstructured":"Bhosale, S., Chakraborty, R., Kopparapu, S.K.: Deep encoded linguistic and acoustic cues for attention based end to end speech emotion recognition. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020), pp. 7189\u20137193. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054621"},{"key":"33_CR18","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"33_CR19","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"33_CR20","unstructured":"Adam, K.D.B.J., et al.: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"33_CR21","doi-asserted-by":"crossref","unstructured":"Guo, L., Wang, L., Xu, C., Dang, J., Chang, E.S., Li, H.: Representation learning with spectro-temporal-channel attention for speech emotion recognition. In: 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021), pp. 6304\u20136308. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Mao, S., Tao, D., Zhang, G., Ching, P., Lee, T.: Revisiting hidden Markov models for speech emotion recognition. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), pp. 6715\u20136719. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683172"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Kim, E., Shin, J.W.: DNN-based emotion recognition based on bottleneck acoustic features and lexical features. In: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), pp. 6720\u20136724. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"33_CR24","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.neucom.2018.05.005","volume":"309","author":"ZT Liu","year":"2018","unstructured":"Liu, Z.T., Xie, Q., Wu, M., Cao, W.H., Mei, Y., Mao, J.W.: Speech emotion recognition based on an improved brain emotion learning model. Neurocomputing 309, 145\u2013156 (2018)","journal-title":"Neurocomputing"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., Tashev, I.: Speech emotion recognition using deep neural network and extreme learning machine. In: Interspeech 2014 (2014)","DOI":"10.21437\/Interspeech.2014-57"},{"key":"33_CR26","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.bspc.2014.10.008","volume":"18","author":"Y Sun","year":"2015","unstructured":"Sun, Y., Wen, G., Wang, J.: Weighted spectral features based on local hu moments for speech emotion recognition. Biomed. Signal Process. Control 18, 80\u201390 (2015)","journal-title":"Biomed. Signal Process. Control"},{"issue":"6","key":"33_CR27","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1109\/TMM.2017.2766843","volume":"20","author":"S Zhang","year":"2017","unstructured":"Zhang, S., Zhang, S., Huang, T., Gao, W.: Speech emotion recognition using deep convolutional neural network and discriminant temporal pyramid matching. IEEE Trans. Multimedia 20(6), 1576\u20131590 (2017)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"33_CR28","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1111\/1467-9280.00037","volume":"9","author":"DM Wegner","year":"1998","unstructured":"Wegner, D.M., Ansfield, M., Pilloff, D.: The putt and the pendulum: ironic effects of the mental control of action. Psychol. Sci. 9(3), 196\u2013199 (1998)","journal-title":"Psychol. Sci."},{"issue":"1","key":"33_CR29","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/TMM.2004.840618","volume":"7","author":"A Hanjalic","year":"2005","unstructured":"Hanjalic, A., Xu, L.Q.: Affective video content representation and modeling. IEEE Trans. Multimedia 7(1), 143\u2013154 (2005)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8138-0_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:35:29Z","timestamp":1710351329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8138-0_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,26]]},"ISBN":["9789819981373","9789819981380"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8138-0_33","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,26]]},"assertion":[{"value":"26 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","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":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.org\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}