{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:11:26Z","timestamp":1757311886484,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030922375"},{"type":"electronic","value":"9783030922382"}],"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\/978-3-030-92238-2_36","type":"book-chapter","created":{"date-parts":[[2021,12,4]],"date-time":"2021-12-04T22:02:35Z","timestamp":1638655355000},"page":"431-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Grouped Echo State Network with\u00a0Late Fusion for\u00a0Speech Emotion Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7602-6838","authenticated-orcid":false,"given":"Hemin","family":"Ibrahim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7867-2665","authenticated-orcid":false,"given":"Chu Kiong","family":"Loo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6102-3765","authenticated-orcid":false,"given":"Fady","family":"Alnajjar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,12,5]]},"reference":[{"key":"36_CR1","doi-asserted-by":"publisher","unstructured":"Al-Talabani, A., Sellahewa, H., Jassim, S.: Excitation source and low level descriptor features fusion for emotion recognition using SVM and ANN. In: 2013 5th Computer Science and Electronic Engineering Conference (CEEC), pp. 156\u2013161 (2013). https:\/\/doi.org\/10.1109\/CEEC.2013.6659464","DOI":"10.1109\/CEEC.2013.6659464"},{"key":"36_CR2","doi-asserted-by":"publisher","unstructured":"Al-Talabani, A., Sellahewa, H., Jassim, S.A.: Emotion recognition from speech: tools and challenges. In: Agaian, S.S., Jassim, S.A., Du, E.Y. (eds.) Mobile Multimedia\/Image Processing, Security, and Applications 2015, vol. 9497, pp. 193\u2013200. International Society for Optics and Photonics, SPIE (2015). https:\/\/doi.org\/10.1117\/12.2191623","DOI":"10.1117\/12.2191623"},{"key":"36_CR3","unstructured":"Bianchi, F.M., Scardapane, S., L\u00f8kse, S., Jenssen, R.: Bidirectional deep-readout echo state networks. In: ESANN (2018)"},{"issue":"2","key":"36_CR4","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TNNLS.2016.2630802","volume":"29","author":"FM Bianchi","year":"2018","unstructured":"Bianchi, F.M., Livi, L., Alippi, C.: Investigating echo-state networks dynamics by means of recurrence analysis. IEEE Trans. Neural Netw. Learn. Syst. 29(2), 427\u2013439 (2018). https:\/\/doi.org\/10.1109\/TNNLS.2016.2630802","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"5","key":"36_CR5","doi-asserted-by":"publisher","first-page":"2169","DOI":"10.1109\/TNNLS.2020.3001377","volume":"32","author":"FM Bianchi","year":"2021","unstructured":"Bianchi, F.M., Scardapane, S., L\u00f8kse, S., Jenssen, R.: Reservoir computing approaches for representation and classification of multivariate time series. IEEE Trans. Neural Netw. Learn. Syst. 32(5), 2169\u20132179 (2021). https:\/\/doi.org\/10.1109\/TNNLS.2020.3001377","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"36_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3404993","volume":"17","author":"L Cerina","year":"2020","unstructured":"Cerina, L., Santambrogio, M.D., Franco, G., Gallicchio, C., Micheli, A.: EchoBay: design and optimization of echo state networks under memory and time constraints. ACM Trans. Archit. Code Optim. 17(3), 1\u201324 (2020). https:\/\/doi.org\/10.1145\/3404993","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"36_CR7","doi-asserted-by":"publisher","unstructured":"Chen, L., Mao, X., Xue, Y., Cheng, L.L.: Speech emotion recognition: features and classification models. Digit. Signal Process. 22(6), 1154\u20131160 (2012). https:\/\/doi.org\/10.1016\/j.dsp.2012.05.007. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1051200412001133","DOI":"10.1016\/j.dsp.2012.05.007"},{"key":"36_CR8","doi-asserted-by":"publisher","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). https:\/\/doi.org\/10.1016\/j.apacoust.2020.107360. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0003682X1931117X","DOI":"10.1016\/j.apacoust.2020.107360"},{"issue":"3","key":"36_CR9","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/TCYB.2017.2787717","volume":"49","author":"S Deb","year":"2019","unstructured":"Deb, S., Dandapat, S.: Multiscale amplitude feature and significance of enhanced vocal tract information for emotion classification. IEEE Trans. Cybern. 49(3), 802\u2013815 (2019). https:\/\/doi.org\/10.1109\/TCYB.2017.2787717","journal-title":"IEEE Trans. Cybern."},{"key":"36_CR10","doi-asserted-by":"publisher","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S.: COVAREP - a collaborative voice analysis repository for speech technologies. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 960\u2013964 (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6853739","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"36_CR11","doi-asserted-by":"publisher","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: OpenSMILE: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, MM 2010, pp. 1459\u20131462. Association for Computing Machinery, New York (2010). https:\/\/doi.org\/10.1145\/1873951.1874246","DOI":"10.1145\/1873951.1874246"},{"key":"36_CR12","doi-asserted-by":"crossref","unstructured":"Gallicchio, C., Micheli, A.: A preliminary application of echo state networks to emotion recognition (2014)","DOI":"10.1016\/j.neucom.2012.08.017"},{"key":"36_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1007\/978-3-030-30493-5_6","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2019: Workshop and Special Sessions","author":"C Gallicchio","year":"2019","unstructured":"Gallicchio, C., Micheli, A.: Reservoir topology in deep echo state networks. In: Tetko, I.V., K\u016frkov\u00e1, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 62\u201375. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30493-5_6"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Haq, S., Jackson, P.: Multimodal emotion recognition. In: Machine Audition: Principles, Algorithms and Systems, pp. 398\u2013423. IGI Global, Hershey, August 2010","DOI":"10.4018\/978-1-61520-919-4.ch017"},{"key":"36_CR15","doi-asserted-by":"publisher","unstructured":"Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78\u201380 (2004). https:\/\/doi.org\/10.1126\/science.1091277. https:\/\/science.sciencemag.org\/content\/304\/5667\/78","DOI":"10.1126\/science.1091277"},{"key":"36_CR16","doi-asserted-by":"publisher","unstructured":"Kathiresan, T., Dellwo, V.: Cepstral derivatives in MFCCS for emotion recognition. In: 2019 IEEE 4th International Conference on Signal and Image Processing (ICSIP), pp. 56\u201360 (2019). https:\/\/doi.org\/10.1109\/SIPROCESS.2019.8868573","DOI":"10.1109\/SIPROCESS.2019.8868573"},{"key":"36_CR17","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":"36_CR18","unstructured":"Lema\u00eetre, G., Nogueira, F., Aridas, C.K.: Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J. Mach. Learn. Res. 18(17), 1\u20135 (2017). http:\/\/jmlr.org\/papers\/v18\/16-365.html"},{"key":"36_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-642-35289-8_36","volume-title":"Neural Networks: Tricks of the Trade","author":"M Luko\u0161evi\u010dius","year":"2012","unstructured":"Luko\u0161evi\u010dius, M.: A practical guide to applying echo state networks. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 659\u2013686. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35289-8_36"},{"key":"36_CR20","doi-asserted-by":"publisher","unstructured":"Luko\u0161evi\u010dius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127\u2013149 (2009). https:\/\/doi.org\/10.1016\/j.cosrev.2009.03.005. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1574013709000173","DOI":"10.1016\/j.cosrev.2009.03.005"},{"key":"36_CR21","doi-asserted-by":"crossref","unstructured":"Maat, J.R., Gianniotis, N., Protopapas, P.: Efficient optimization of echo state networks for time series datasets. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137 (2018)","DOI":"10.1109\/IJCNN.2018.8489094"},{"issue":"8","key":"36_CR22","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. Multimed. 16(8), 2203\u20132213 (2014). https:\/\/doi.org\/10.1109\/TMM.2014.2360798","journal-title":"IEEE Trans. Multimed."},{"key":"36_CR23","doi-asserted-by":"publisher","unstructured":"Mustaqeem, Sajjad, M., Kwon, S.: Clustering-based speech emotion recognition by incorporating learned features and deep BiLSTM. IEEE Access 8, 79861\u201379875 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2990405","DOI":"10.1109\/ACCESS.2020.2990405"},{"key":"36_CR24","unstructured":"Nogueira, F.: Bayesian optimization: open source constrained global optimization tool for Python (2014). https:\/\/github.com\/fmfn\/BayesianOptimization"},{"key":"36_CR25","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.apacoust.2018.11.028","volume":"146","author":"T \u00d6zseven","year":"2019","unstructured":"\u00d6zseven, T.: A novel feature selection method for speech emotion recognition. Appl. Acoust. 146, 320\u2013326 (2019)","journal-title":"Appl. Acoust."},{"key":"36_CR26","doi-asserted-by":"publisher","unstructured":"Saleh, Q., Merkel, C., Kudithipudi, D., Wysocki, B.: Memristive computational architecture of an echo state network for real-time speech-emotion recognition. In: 2015 IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA), pp. 1\u20135 (2015). https:\/\/doi.org\/10.1109\/CISDA.2015.7208624","DOI":"10.1109\/CISDA.2015.7208624"},{"key":"36_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1007\/978-3-540-69369-7_22","volume-title":"Perception in Multimodal Dialogue Systems","author":"S Scherer","year":"2008","unstructured":"Scherer, S., Oubbati, M., Schwenker, F., Palm, G.: Real-time emotion recognition using echo state networks. In: Andr\u00e9, E., Dybkj\u00e6r, L., Minker, W., Neumann, H., Pieraccini, R., Weber, M. (eds.) PIT 2008. LNCS (LNAI), vol. 5078, pp. 200\u2013204. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-69369-7_22"},{"key":"36_CR28","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A.: The interspeech 2009 emotion challenge. In: Tenth Annual Conference of the International Speech Communication Association (2009)","DOI":"10.21437\/Interspeech.2009-103"},{"key":"36_CR29","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 2, NIPS 2012, pp. 2951\u20132959. Curran Associates Inc., Red Hook (2012)"},{"key":"36_CR30","unstructured":"Steidl, S.: Automatic Classification of Emotion Related User States in Spontaneous Children\u2019s Speech. Logos-Verlag (2009)"},{"key":"36_CR31","doi-asserted-by":"publisher","unstructured":"Triantafyllopoulos, A., Liu, S., Schuller, B.W.: Deep speaker conditioning for speech emotion recognition. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2021). https:\/\/doi.org\/10.1109\/ICME51207.2021.9428217","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"36_CR32","doi-asserted-by":"crossref","unstructured":"Wen, G., Li, H., Huang, J., Li, D., Xun, E.: Random deep belief networks for recognizing emotions from speech signals. Comput. Intell. Neurosci. 2017 (2017)","DOI":"10.1155\/2017\/1945630"},{"key":"36_CR33","unstructured":"Wu, Q., Fokoue, E., Kudithipudi, D.: On the statistical challenges of echo state networks and some potential remedies (2018)"},{"key":"36_CR34","doi-asserted-by":"publisher","first-page":"97515","DOI":"10.1109\/ACCESS.2019.2928625","volume":"7","author":"Z Zhao","year":"2019","unstructured":"Zhao, Z., et al.: Exploring deep spectrum representations via attention-based recurrent and convolutional neural networks for speech emotion recognition. IEEE Access 7, 97515\u201397525 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2928625","journal-title":"IEEE Access"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92238-2_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T18:55:54Z","timestamp":1710356154000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92238-2_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030922375","9783030922382"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92238-2_36","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":"5 December 2021","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":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","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":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.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":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}