{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:37:56Z","timestamp":1743089876146,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030930486"},{"type":"electronic","value":"9783030930493"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-93049-3_22","type":"book-chapter","created":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T06:00:24Z","timestamp":1641016824000},"page":"261-272","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Syllable Level Speech Emotion Recognition Based on\u00a0Formant Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2345-2256","authenticated-orcid":false,"given":"Abdul","family":"Rehman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4100-9557","authenticated-orcid":false,"given":"Zhen-Tao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin-Meng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,1]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Aldeneh, Z., Provost, E.M.: Using regional saliency for speech emotion recognition. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2741\u20132745. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952655"},{"issue":"4","key":"22_CR2","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 (2008)","journal-title":"Lang. Resour. Eval."},{"issue":"1","key":"22_CR3","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/TAFFC.2016.2515617","volume":"8","author":"C Busso","year":"2016","unstructured":"Busso, C., Parthasarathy, S., Burmania, A., AbdelWahab, M., Sadoughi, N., Provost, E.M.: MSP-IMPROV: an acted corpus of dyadic interactions to study emotion perception. IEEE Trans. Affect. Comput. 8(1), 67\u201380 (2016)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"22_CR4","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.csl.2014.01.003","volume":"29","author":"H Cao","year":"2015","unstructured":"Cao, H., Verma, R., Nenkova, A.: Speaker-sensitive emotion recognition via ranking: studies on acted and spontaneous speech. Comput. Speech Lang. 29(1), 186\u2013202 (2015)","journal-title":"Comput. Speech Lang."},{"issue":"10","key":"22_CR5","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1109\/LSP.2018.2860246","volume":"25","author":"M Chen","year":"2018","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. 25(10), 1440\u20131444 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"22_CR6","doi-asserted-by":"publisher","first-page":"107360","DOI":"10.1016\/j.apacoust.2020.107360","volume":"166","author":"F Daneshfar","year":"2020","unstructured":"Daneshfar, F., Kabudian, S.J., Neekabadi, A.: Speech emotion recognition using hybrid spectral-prosodic features of speech signal\/glottal waveform, metaheuristic-based dimensionality reduction, and gaussian elliptical basis function network classifier. Appl. Acoust. 166, 107360 (2020)","journal-title":"Appl. Acoust."},{"issue":"6","key":"22_CR7","first-page":"1","volume":"1","author":"N Dave","year":"2013","unstructured":"Dave, N.: Feature extraction methods LPC, PLP and MFCC in speech recognition. Int. J. Adv. Res. Eng. Technol. 1(6), 1\u20134 (2013)","journal-title":"Int. J. Adv. Res. Eng. Technol."},{"key":"22_CR8","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":"22_CR9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2017.02.013","volume":"92","author":"HM Fayek","year":"2017","unstructured":"Fayek, H.M., Lech, M., Cavedon, L.: Evaluating deep learning architectures for speech emotion recognition. Neural Netw. 92, 60\u201368 (2017)","journal-title":"Neural Netw."},{"issue":"5","key":"22_CR10","doi-asserted-by":"publisher","first-page":"479","DOI":"10.3390\/e21050479","volume":"21","author":"N Hajarolasvadi","year":"2019","unstructured":"Hajarolasvadi, N., Demirel, H.: 3d CNN-based speech emotion recognition using k-means clustering and spectrograms. Entropy 21(5), 479 (2019)","journal-title":"Entropy"},{"key":"22_CR11","doi-asserted-by":"publisher","first-page":"101894","DOI":"10.1016\/j.bspc.2020.101894","volume":"59","author":"D Issa","year":"2020","unstructured":"Issa, D., Demirci, M.F., Yazici, A.: Speech emotion recognition with deep convolutional neural networks. Biomed. Signal Process. Control 59, 101894 (2020)","journal-title":"Biomed. Signal Process. Control"},{"issue":"1","key":"22_CR12","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s10772-020-09672-4","volume":"23","author":"A Koduru","year":"2020","unstructured":"Koduru, A., Valiveti, H.B., Budati, A.K.: Feature extraction algorithms to improve the speech emotion recognition rate. Int. J. Speech Technol. 23(1), 45\u201355 (2020)","journal-title":"Int. J. Speech Technol."},{"key":"22_CR13","unstructured":"Lakomkin, E., Weber, C., Magg, S., Wermter, S.: Reusing neural speech representations for auditory emotion recognition. arXiv preprint arXiv:1803.11508 (2018)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Le, D., Aldeneh, Z., Provost, E.M.: Discretized continuous speech emotion recognition with multi-task deep recurrent neural network. In: INTERSPEECH, pp. 1108\u20131112 (2017)","DOI":"10.21437\/Interspeech.2017-94"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Lee, J., Tashev, I.: High-level feature representation using recurrent neural network for speech emotion recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (2015)","DOI":"10.21437\/Interspeech.2015-336"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Lee, S.w.: Domain generalization with triplet network for cross-corpus speech emotion recognition. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 389\u2013396. IEEE (2021)","DOI":"10.1109\/SLT48900.2021.9383534"},{"key":"22_CR17","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.ins.2021.02.016","volume":"563","author":"ZT Liu","year":"2021","unstructured":"Liu, Z.T., Rehman, A., Wu, M., Cao, W.H., Hao, M.: Speech emotion recognition based on formant characteristics feature extraction and phoneme type convergence. Inf. Sci. 563, 309\u2013325 (2021)","journal-title":"Inf. Sci."},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Mirsamadi, S., Barsoum, E., Zhang, C.: Automatic speech emotion recognition using recurrent neural networks with local attention. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2227\u20132231. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"22_CR19","first-page":"506","volume":"2020","author":"BH Su","year":"2020","unstructured":"Su, B.H., Chang, C.M., Lin, Y.S., Lee, C.C.: Improving speech emotion recognition using graph attentive bi-directional gated recurrent unit network. Proc. Interspeech 2020, 506\u2013510 (2020)","journal-title":"Proc. Interspeech"},{"key":"22_CR20","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: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6474\u20136478. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9054629"},{"key":"22_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.specom.2020.03.005","volume":"120","author":"Z Yao","year":"2020","unstructured":"Yao, Z., Wang, Z., Liu, W., Liu, Y., Pan, J.: Speech emotion recognition using fusion of three multi-task learning-based classifiers: HSF-DNN, MS-CNN and LLD-RNN. Speech Commun. 120, 11\u201319 (2020)","journal-title":"Speech Commun."},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Zhang, S., Zhao, X., Tian, Q.: Spontaneous speech emotion recognition using multiscale deep convolutional LSTM. IEEE Transactions on Affective Computing, p. 1 (2019). https:\/\/doi.org\/10.1109\/TAFFC.2019.2947464","DOI":"10.1109\/TAFFC.2019.2947464"},{"issue":"6","key":"22_CR23","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"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-93049-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T06:27:39Z","timestamp":1641018459000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-93049-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030930486","9783030930493"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-93049-3_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","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":"105","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":"34% - 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":"3.2","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":"5.3","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)"}}]}}