{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T09:52:22Z","timestamp":1743155542673,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031084201"},{"type":"electronic","value":"9783031084218"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-08421-8_24","type":"book-chapter","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T21:02:38Z","timestamp":1658178158000},"page":"348-358","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Static, Dynamic and\u00a0Acceleration Features for\u00a0CNN-Based Speech Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Intissar","family":"Khalifa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8148-1621","authenticated-orcid":false,"given":"Ridha","family":"Ejbali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9112-0574","authenticated-orcid":false,"given":"Paolo","family":"Napoletano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7461-1451","authenticated-orcid":false,"given":"Raimondo","family":"Schettini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4013-5834","authenticated-orcid":false,"given":"Mourad","family":"Zaied","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"issue":"5","key":"24_CR1","doi-asserted-by":"publisher","first-page":"5571","DOI":"10.1007\/s11042-017-5292-7","volume":"78","author":"AM Badshah","year":"2017","unstructured":"Badshah, A.M., Rahim, N., Ullah, N., Ahmad, J., Muhammad, K., Lee, M.Y., Kwon, S., Baik, S.W.: Deep features-based speech emotion recognition for smart affective services. Multimedia Tools Appl. 78(5), 5571\u20135589 (2017). https:\/\/doi.org\/10.1007\/s11042-017-5292-7","journal-title":"Multimedia Tools Appl."},{"key":"24_CR2","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neucom.2017.01.096","volume":"253","author":"P Barros","year":"2017","unstructured":"Barros, P., Parisi, G.I., Weber, C., Wermter, S.: Emotion-modulated attention improves expression recognition: a deep learning model. Neurocomputing 253, 104\u2013114 (2017)","journal-title":"Neurocomputing"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B.: A database of German emotional speech. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"3","key":"24_CR4","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recognit. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recognit."},{"key":"24_CR5","unstructured":"Ganchev, T., Fakotakis, N., Kokkinakis, G.: Comparative evaluation of various MFCC implementations on the speaker verification task. In: Proceedings of the SPECOM, vol. 1, pp. 191\u2013194 (2005)"},{"key":"24_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-70772-3_1","volume-title":"Brain Informatics","author":"Y Gao","year":"2017","unstructured":"Gao, Y., Li, B., Wang, N., Zhu, T.: Speech emotion recognition using local and global features. In: Zeng, Y., et al. (eds.) BI 2017. LNCS (LNAI), vol. 10654, pp. 3\u201313. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70772-3_1"},{"key":"24_CR7","unstructured":"Gu, Y., Postma, E., Lin, H.X., Herik, J.V.D.: Speech emotion recognition using voiced segment selection algorithm. In: Proceedings of the Twenty-second European Conference on Artificial Intelligence, pp. 1682\u20131683. IOS Press (2016)"},{"issue":"2","key":"24_CR8","first-page":"47","volume":"20","author":"A Hans","year":"2015","unstructured":"Hans, A., Hans, E.: Kinesics haptics, and proxemics: aspects of non-verbal communication. IOSR J. Humanit. Soc. Sci. (IOSR-JHSS) 20(2), 47\u201352 (2015)","journal-title":"IOSR J. Humanit. Soc. Sci. (IOSR-JHSS)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Hanson, B.A., Applebaum, T.H.: Robust speaker-independent word recognition using static, dynamic and acceleration features: experiments with Lombard and noisy speech. In: International Conference on Acoustics, Speech, and Signal Processing, pp. 857\u2013860. IEEE (1990)","DOI":"10.1109\/ICASSP.1990.115973"},{"issue":"4","key":"24_CR10","first-page":"565","volume":"1","author":"MR Hasan","year":"2004","unstructured":"Hasan, M.R., Jamil, M., Rahman, M., et al.: Speaker identification using mel frequency cepstral coefficients. Variations 1(4), 565\u2013568 (2004)","journal-title":"Variations"},{"key":"24_CR11","unstructured":"Ingale, A.B., Chaudhari, D., Ingale Ashish, B., et al.: Speech emotion recognition using hidden Markov model and support vector machine (2012)"},{"key":"24_CR12","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-981-13-5907-1_29","volume-title":"Parallel and Distributed Computing, Applications and Technologies","author":"I Khalifa","year":"2019","unstructured":"Khalifa, I., Ejbali, R., Zaied, M.: Body gesture modeling for psychology analysis in job interview based on deep spatio-temporal approach. In: Park, J.H., Shen, H., Sung, Y., Tian, H. (eds.) PDCAT 2018. CCIS, vol. 931, pp. 274\u2013284. Springer, Singapore (2019). https:\/\/doi.org\/10.1007\/978-981-13-5907-1_29"},{"issue":"8","key":"24_CR13","doi-asserted-by":"publisher","first-page":"5455","DOI":"10.1007\/s10462-020-09825-6","volume":"53","author":"A Khan","year":"2020","unstructured":"Khan, A., Sohail, A., Zahoora, U., Qureshi, A.S.: A survey of the recent architectures of deep convolutional neural networks. Artif. Intell. Rev. 53(8), 5455\u20135516 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09825-6","journal-title":"Artif. Intell. Rev."},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Lampropoulos, A.S., Tsihrintzis, G.A.: Evaluation of mpeg-7 descriptors for speech emotional recognition. In: 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 98\u2013101. IEEE (2012)","DOI":"10.1109\/IIH-MSP.2012.29"},{"issue":"5","key":"24_CR15","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 Ryerson 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(5), e0196391 (2018)","journal-title":"PloS One"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Ly, S.T., Lee, G.S., Kim, S.H., Yang, H.J.: Emotion recognition via body gesture: deep learning model coupled with keyframe selection. In: Proceedings of the 2018 International Conference on Machine Learning and Machine Intelligence, pp. 27\u201331 (2018)","DOI":"10.1145\/3278312.3278313"},{"key":"24_CR17","unstructured":"Majeed, S.A., Husain, H., Samad, S.A., Idbeaa, T.F.: Mel frequency cepstral coefficients (MFCC) feature extraction enhancement in the application of speech recognition: a comparison study. J. Theor. Appl. Inf. Technol. 79(1) (2015)"},{"key":"24_CR18","unstructured":"Mehrabian, A.: Communication without words. Psychol. Today, 2(4) (1968)"},{"key":"24_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.bica.2016.12.002","volume":"19","author":"S Motamed","year":"2017","unstructured":"Motamed, S., Setayeshi, S., Rabiee, A.: Speech emotion recognition based on a modified brain emotional learning model. Biologically Inspired Cognitive Architectures 19, 32\u201338 (2017)","journal-title":"Biologically Inspired Cognitive Architectures"},{"issue":"2","key":"24_CR20","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1109\/TAFFC.2018.2874986","volume":"12","author":"F Noroozi","year":"2018","unstructured":"Noroozi, F., Kaminska, D., Corneanu, C., Sapinski, T., Escalera, S., Anbarjafari, G.: Survey on emotional body gesture recognition. IEEE Trans. Affect. Comput. 12(2), 505\u2013523 (2018)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Parry, J., et al.: Analysis of deep learning architectures for cross-corpus speech emotion recognition. In: Proceedings Interspeech, vol. 2019, 1656\u20131660 (2019)","DOI":"10.21437\/Interspeech.2019-2753"},{"key":"24_CR22","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/978-3-319-66604-4_18","volume-title":"Advances in Neural Computation, Machine Learning, and Cognitive Research","author":"AS Popova","year":"2018","unstructured":"Popova, A.S., Rassadin, A.G., Ponomarenko, A.A.: Emotion recognition in sound. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V. (eds.) NEUROINFORMATICS 2017. SCI, vol. 736, pp. 117\u2013124. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-66604-4_18"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Prasomphan, S.: Improvement of speech emotion recognition with neural network classifier by using speech spectrogram. In: 2015 International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 73\u201376. IEEE (2015)","DOI":"10.1109\/IWSSIP.2015.7314180"},{"key":"24_CR24","unstructured":"Rabiner, L.: Fundamentals of speech recognition (1993)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Shegokar, P., Sircar, P.: Continuous wavelet transform based speech emotion recognition. In: 2016 10th International Conference on Signal Processing and Communication Systems (ICSPCS), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/ICSPCS.2016.7843306"},{"key":"24_CR26","doi-asserted-by":"crossref","unstructured":"Singh, N., Khan, R., Shree, R.: MFCC and prosodic feature extraction techniques: a comparative study. Int. J. Comput. Appl. 54(1) (2012)","DOI":"10.5120\/8529-2061"},{"issue":"11","key":"24_CR27","first-page":"3293","volume":"6","author":"GD Sree","year":"2016","unstructured":"Sree, G.D., Chandrasekhar, P., Venkatesshulu, B.: SVM based speech emotion recognition compared with GMM-UBM and NN. IJESC 6(11), 3293\u20133298 (2016)","journal-title":"IJESC"},{"key":"24_CR28","unstructured":"Sun, Y., Xue, B., Zhang, M., Yen, G.G.: Automatically designing CNN architectures using genetic algorithm for image classification. arXiv preprint arXiv:1808.03818 (2018)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Tanmoy, R., Snehashish, C., Tshilidzi, M., Paul, S.: Introducing new feature set based on wavelets for speech emotion classification. In: 2018 IEEE Applied Signal Processing Conference (ASPCON), pp. 124\u2013128. IEEE (2018)","DOI":"10.1109\/ASPCON.2018.8748666"},{"key":"24_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1007\/978-3-540-85099-1_7","volume-title":"Affect and Emotion in Human-Computer Interaction","author":"T Vogt","year":"2008","unstructured":"Vogt, T., Andr\u00e9, E., Wagner, J.: Automatic recognition of emotions from speech: a review of the literature and recommendations for practical realisation. In: Peter, C., Beale, R. (eds.) Affect and Emotion in Human-Computer Interaction. LNCS, vol. 4868, pp. 75\u201391. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-85099-1_7"},{"key":"24_CR31","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/978-3-642-00525-1_26","volume-title":"Multimodal Signals: Cognitive and Algorithmic Issues","author":"M Vondra","year":"2009","unstructured":"Vondra, M., V\u00edch, R.: Recognition of emotions in German speech using gaussian mixture models. In: Esposito, A., Hussain, A., Marinaro, M., Martone, R. (eds.) Multimodal Signals: Cognitive and Algorithmic Issues. LNCS (LNAI), vol. 5398, pp. 256\u2013263. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-00525-1_26"},{"issue":"2","key":"24_CR32","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1177\/1754073917749880","volume":"11","author":"Z Witkower","year":"2019","unstructured":"Witkower, Z., Tracy, J.L.: Bodily communication of emotion: evidence for extrafacial behavioral expressions and available coding systems. Emot. Rev. 11(2), 184\u2013193 (2019)","journal-title":"Emot. Rev."},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Zamil, A.A.A., Hasan, S., Baki, S.M.J., Adam, J.M., Zaman, I.: Emotion detection from speech signals using voting mechanism on classified frames. In: 2019 International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST), pp. 281\u2013285. IEEE (2019)","DOI":"10.1109\/ICREST.2019.8644168"}],"container-title":["Lecture Notes in Computer Science","AIxIA 2021 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08421-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T10:14:57Z","timestamp":1727604897000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08421-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031084201","9783031084218"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08421-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aixia2021.disco.unimib.it\/","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":"58","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":"36","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":"62% - 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","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","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)"}}]}}