{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:34:04Z","timestamp":1743129244183,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030711863"},{"type":"electronic","value":"9783030711870"}],"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\/978-3-030-71187-0_114","type":"book-chapter","created":{"date-parts":[[2021,6,2]],"date-time":"2021-06-02T05:04:54Z","timestamp":1622610294000},"page":"1230-1237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Statistical Based Modeling Approach for Deep Learning Based Speech Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Sara","family":"Sekkate","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Khalil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdellah","family":"Adib","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,6,3]]},"reference":[{"issue":"1","key":"114_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s12559-013-9229-9","volume":"7","author":"K L\u00f3pez-de Ipi\u00f1a","year":"2015","unstructured":"L\u00f3pez-de Ipi\u00f1a, K., Alonso, J.B., Sol\u00e9-Casals, J., Barroso, N., Henriquez, P., Faundez-Zanuy, M., Travieso, C.M., Ecay-Torres, M., Mart\u00ednez-Lage, P., Eguiraun, H.: On automatic diagnosis of Alzheimer\u2019s disease based on spontaneous speech analysis and emotional temperature. Cogn. Comput. 7(1), 44\u201355 (2015)","journal-title":"Cogn. Comput."},{"unstructured":"Petrushin, V.A.: Emotion in speech recognition and application to call centers. In: Proceedings of Artificial Neural Networks In Engineering (ANNIE 99), pp. 7\u201310 (1999)","key":"114_CR2"},{"doi-asserted-by":"crossref","unstructured":"Riyad, M., Khalil, M., Adib, A.: Incep-EEGNet: a convnet for motor imagery decoding. In: Moataz, A.E., Mammass, D., Mansouri, A., Nouboud, F., (eds.) Image and Signal Processing - 9th International Conference, ICISP 2020, Marrakesh, Morocco, 4\u20136 June 2020, Proceedings, volume 12119 of Lecture Notes in Computer Science, pp. 103\u2013111. Springer, Cham (2020)","key":"114_CR3","DOI":"10.1007\/978-3-030-51935-3_11"},{"doi-asserted-by":"crossref","unstructured":"Bouny, L.E., Khalil, M., Adib, A.: ECG heartbeat classification based on multi-scale wavelet convolutional neural networks. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, 4\u20138 May 2020, pp. 3212\u20133216. IEEE (2020)","key":"114_CR4","DOI":"10.1109\/ICASSP40776.2020.9054749"},{"doi-asserted-by":"crossref","unstructured":"Trigeorgis, G.,\u00a0Ringeval, F.,\u00a0Brueckner, R.,\u00a0Marchi, E., Nicolaou, M.A.,\u00a0Schuller, B., \u00a0Zafeiriou, S.: Adieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5200\u20135204 (2016)","key":"114_CR5","DOI":"10.1109\/ICASSP.2016.7472669"},{"doi-asserted-by":"crossref","unstructured":"Ringeval, F.,\u00a0Sonderegger, A.,\u00a0Sauer, J.,\u00a0Lalanne, D.: Introducing the recola multimodal corpus of remote collaborative and affective interactions. In: EmoSPACE (2013)","key":"114_CR6","DOI":"10.1109\/FG.2013.6553805"},{"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 (Sept 2014)","key":"114_CR7","DOI":"10.21437\/Interspeech.2014-57"},{"doi-asserted-by":"crossref","unstructured":"Pandey, S.K., Shekhawat, H.S., Prasanna, S.R.M.: Emotion recognition from raw speech using wavenet. In: TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), pp. 1292\u20131297 (2019)","key":"114_CR8","DOI":"10.1109\/TENCON.2019.8929257"},{"doi-asserted-by":"crossref","unstructured":"Badshah, A.M.,\u00a0Ahmad, J.,\u00a0Rahim, N., Baik, S.W.: Speech emotion recognition from spectrograms with deep convolutional neural network. In: 2017 International Conference on Platform Technology and Service (PlatCon), pp. 1\u20135 (2017)","key":"114_CR9","DOI":"10.1109\/PlatCon.2017.7883728"},{"issue":"8","key":"114_CR10","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"},{"doi-asserted-by":"crossref","unstructured":"Huang, Z., Dong, M., Mao, Q., Zhan, Y.: Speech emotion recognition using CNN. In: Proceedings of the 22nd ACM International Conference on Multimedia, MM 2014, pp. 801\u2013804, New York, NY, USA (2014). Association for Computing Machinery","key":"114_CR11","DOI":"10.1145\/2647868.2654984"},{"issue":"10","key":"114_CR12","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."},{"doi-asserted-by":"crossref","unstructured":"Hifny, Y.,\u00a0Ali, A.: Efficient Arabic emotion recognition using deep neural networks. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6710\u20136714 (2019)","key":"114_CR13","DOI":"10.1109\/ICASSP.2019.8683632"},{"unstructured":"Meftah, A., Alotaibi, Y.A., Selouani, S.A.: Designing, building, and analyzing an Arabic speech emotional corpus: phase 2. In: 5th International Conference on Arabic Language Processing, pp. 181\u2013184 (2014)","key":"114_CR14"},{"doi-asserted-by":"crossref","unstructured":"Sugan, N., Sai Srinivas, N.S.,\u00a0Kar, N., Kumar, L.S., Nath, M.K.,\u00a0Kanhe, A.: Performance comparison of different cepstral features for speech emotion recognition. In: 2018 International CET Conference on Control, Communication, and Computing (IC4), pp. 266\u2013271 (2018)","key":"114_CR15","DOI":"10.1109\/CETIC4.2018.8531065"},{"key":"114_CR16","doi-asserted-by":"publisher","first-page":"101894","DOI":"10.1016\/j.bspc.2020.101894","volume":"59","author":"D Issa","year":"2020","unstructured":"Issa, D., Fatih Demirci, M., Yazici, A.: Speech emotion recognition with deep convolutional neural networks. Biomed. Signal Process. Control 59, 101894 (2020)","journal-title":"Biomed. Signal Process. Control"},{"key":"114_CR17","doi-asserted-by":"publisher","first-page":"937","DOI":"10.21437\/Interspeech.2018-1132","volume":"2018","author":"J Kim","year":"2018","unstructured":"Kim, J., Saurous, R.A.: Emotion recognition from human speech using temporal information and deep learning. Proc. Interspeech 2018, 937\u2013940 (2018)","journal-title":"Proc. Interspeech"},{"doi-asserted-by":"crossref","unstructured":"Lakomkin, E., Zamani, M.A.,\u00a0Weber, C.,\u00a0Magg, S.,\u00a0Wermter, 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), pp. 854\u2013860 (2018)","key":"114_CR18","DOI":"10.1109\/IROS.2018.8593571"},{"doi-asserted-by":"crossref","unstructured":"Yenigalla, P., Kumar, A.,\u00a0Tripathi, S.,\u00a0Singh, C.,\u00a0Kar, S.,\u00a0Vepa, J.: Speech emotion recognition using spectrogram & phoneme embedding. In: INTERSPEECH (2018)","key":"114_CR19","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"114_CR20","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"Zhao, J., Mao, X., Chen, L.: Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed. Signal Process. Control 47, 312\u2013323 (2019)","journal-title":"Biomed. Signal Process. Control"},{"issue":"4","key":"114_CR21","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3390\/computers8040091","volume":"8","author":"S Sekkate","year":"2019","unstructured":"Sekkate, S., Khalil, M., Adib, A., Ben Jebara, S.: An investigation of a feature-level fusion for noisy speech emotion recognition. Computers 8(4), 91 (2019)","journal-title":"Computers"},{"key":"114_CR22","doi-asserted-by":"publisher","first-page":"2403","DOI":"10.1016\/j.procs.2020.03.293","volume":"167","author":"MB Bora","year":"2020","unstructured":"Bora, M.B., Daimary, D., Amitab, K., Kandar, D.: Handwritten character recognition from images using CNN-ECOC. Procedia Comput. Sci. 167, 2403\u20132409 (2020). International Conference on Computational Intelligence and Data Science","journal-title":"Procedia Comput. Sci."},{"doi-asserted-by":"crossref","unstructured":"McFee, B.,\u00a0Raffel, C.,\u00a0Liang, D., Ellis, D.P.W.,\u00a0McVicar, M.,\u00a0Battenberg, E.,\u00a0Nieto, O.: librosa : Audio and music signal analysis in python (2015)","key":"114_CR23","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"56","key":"114_CR24","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"crossref","unstructured":"Wu, H.,\u00a0Gu, X.: Max-pooling dropout for regularization of convolutional neural networks. In: Neural Information Processing, pp. 46\u201354 (2015)","key":"114_CR25","DOI":"10.1007\/978-3-319-26532-2_6"},{"key":"114_CR26","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S.R., Russo, F.A.: The Rryerson audio-visual database of emotional speech and song (RAVDESS): a dynamic, multimodal set of facial and vocal expressions in north American English. PLoS One 13, e0196391 (2018)","journal-title":"PLoS One"},{"doi-asserted-by":"crossref","unstructured":"Mustaqeem, Kwon, S.: A CNN-assisted enhanced audio signal processing for speech emotion recognition. Sensors 20(1), 183 (2020)","key":"114_CR27","DOI":"10.3390\/s20010183"},{"issue":"3","key":"114_CR28","doi-asserted-by":"publisher","first-page":"3705","DOI":"10.1007\/s11042-017-5539-3","volume":"78","author":"Y Zeng","year":"2019","unstructured":"Zeng, Y., Mao, H., Peng, D., Yi, Z.: Spectrogram based multi-task audio classification. Multimedia Tools Appl. 78(3), 3705\u20133722 (2019)","journal-title":"Multimedia Tools Appl."},{"doi-asserted-by":"crossref","unstructured":"Sefara, T.J.; The effects of normalisation methods on speech emotion recognition. In: 2019 International Multidisciplinary Information Technology and Engineering Conference (IMITEC), pp. 1\u20138 (2019)","key":"114_CR29","DOI":"10.1109\/IMITEC45504.2019.9015895"},{"doi-asserted-by":"crossref","unstructured":"Christy, A.,\u00a0Vaithyasubramanian, S.,\u00a0Jesudoss, A., et\u00a0al.: Multimodal speech emotion recognition and classification using convolutional neural network techniques. In: Int. J. Speech Technol. 23, 381\u2013388 (2020)","key":"114_CR30","DOI":"10.1007\/s10772-020-09713-y"},{"doi-asserted-by":"crossref","unstructured":"Mansouri-Benssassi, E.,\u00a0Ye, J.: Speech emotion recognition with early visual cross-modal enhancement using spiking neural networks. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2019)","key":"114_CR31","DOI":"10.1109\/IJCNN.2019.8852473"}],"container-title":["Advances in Intelligent Systems and Computing","Intelligent Systems Design and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-71187-0_114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T10:55:14Z","timestamp":1672311314000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-71187-0_114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030711863","9783030711870"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-71187-0_114","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"3 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISDA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Systems Design and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isda2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mirlabs.net\/isda20\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}