{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T23:33:45Z","timestamp":1773704025083,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"32","license":[{"start":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T00:00:00Z","timestamp":1723161600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T00:00:00Z","timestamp":1723161600000},"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":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s00521-024-10249-4","type":"journal-article","created":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T14:02:52Z","timestamp":1723212172000},"page":"19939-19950","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Toward an emotion efficient architecture based on the sound spectrum from the voice of Portuguese speakers"],"prefix":"10.1007","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6795-2768","authenticated-orcid":false,"given":"Geraldo P. Rocha","family":"Filho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rodolfo I.","family":"Meneguette","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F\u00e1bio L\u00facio Lopes de","family":"Mendon\u00e7a","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liriam","family":"Enamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustavo","family":"Pessin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vin\u00edcius P.","family":"Gon\u00e7alves","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,9]]},"reference":[{"issue":"10","key":"10249_CR1","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid O, Ar Mohamed, Jiang H, Deng L, Penn G, Yu D (2014) Convolutional neural networks for speech recognition. IEEE\/ACM Trans Audio, Speech, Lang Process 22(10):1533\u20131545","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"issue":"8","key":"10249_CR2","doi-asserted-by":"publisher","first-page":"4750","DOI":"10.3390\/app13084750","volume":"13","author":"AS Alluhaidan","year":"2023","unstructured":"Alluhaidan AS, Saidani O, Jahangir R, Nauman MA, Neffati OS (2023) Speech emotion recognition through hybrid features and convolutional neural network. Appl Sci 13(8):4750","journal-title":"Appl Sci"},{"issue":"3","key":"10249_CR3","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1037\/0022-3514.70.3.614","volume":"70","author":"R Banse","year":"1996","unstructured":"Banse R, Scherer KR (1996) Acoustic profiles in vocal emotion expression. J Pers Soc Psychol 70(3):614","journal-title":"J Pers Soc Psychol"},{"key":"10249_CR4","doi-asserted-by":"publisher","first-page":"113265","DOI":"10.1016\/j.eswa.2020.113265","volume":"150","author":"ML Barr\u00f3n Estrada","year":"2020","unstructured":"Barr\u00f3n Estrada ML, Zatarain Cabada R, Oramas Bustillos R, Graff M (2020) Opinion mining and emotion recognition applied to learning environments. Expert Syst Appl 150:113265. https:\/\/doi.org\/10.1016\/j.eswa.2020.113265","journal-title":"Expert Syst Appl"},{"key":"10249_CR5","unstructured":"Bergstra JS, Bardenet R, Bengio Y, K\u00e9gl B (2011) Algorithms for hyper-parameter optimization. Advances in neural information processing systems 2546\u20132554"},{"key":"10249_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/app10134653","author":"M Bojani\u0107","year":"2020","unstructured":"Bojani\u0107 M, Deli\u0107 V, Karpov A (2020) Call redistribution for a call center based on speech emotion recognition. Appl Sci. https:\/\/doi.org\/10.3390\/app10134653","journal-title":"Appl Sci"},{"key":"10249_CR7","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee CC, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) Iemocap: Interactive emotional dyadic motion capture database. Lang Res Eval 42:335\u2013359","journal-title":"Lang Res Eval"},{"key":"10249_CR8","doi-asserted-by":"publisher","first-page":"118943","DOI":"10.1016\/j.eswa.2022.118943","volume":"214","author":"Z Chen","year":"2023","unstructured":"Chen Z, Li J, Liu H, Wang X, Wang H, Zheng Q (2023) Learning multi-scale features for speech emotion recognition with connection attention mechanism. Expert Syst Appl 214:118943","journal-title":"Expert Syst Appl"},{"key":"10249_CR9","doi-asserted-by":"crossref","unstructured":"Dellaert F, Polzin T, Waibel A (1996) Recognizing emotion in speech. In: Proceeding of fourth international conference on spoken language processing. ICSLP\u201996, vol.\u00a03, pp. 1970\u20131973. IEEE","DOI":"10.1109\/ICSLP.1996.608022"},{"issue":"3","key":"10249_CR10","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 MS, Karray F (2011) Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recognit 44(3):572\u2013587","journal-title":"Pattern Recognit"},{"key":"10249_CR11","doi-asserted-by":"crossref","unstructured":"Eyben F, W\u00f6llmer M, Schuller B (2010) Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM international conference on Multimedia, pp. 1459\u20131462","DOI":"10.1145\/1873951.1874246"},{"key":"10249_CR12","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2017.02.013","volume":"92","author":"HM Fayek","year":"2017","unstructured":"Fayek HM, Lech M, Cavedon L (2017) Evaluating deep learning architectures for speech emotion recognition. Neural Netw 92:60\u201368","journal-title":"Neural Netw"},{"issue":"2","key":"10249_CR13","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1007\/s10489-016-0842-7","volume":"46","author":"VP Gon\u00e7alves","year":"2017","unstructured":"Gon\u00e7alves VP, Costa EP, Valejo A, Geraldo Filho P, Johnson TM, Pessin G, Ueyama J (2017) Enhancing intelligence in multimodal emotion assessments. Appl Intell 46(2):470\u2013486","journal-title":"Appl Intell"},{"issue":"18","key":"10249_CR14","doi-asserted-by":"publisher","first-page":"5309","DOI":"10.1007\/s00500-016-2115-0","volume":"21","author":"VP Gon\u00e7alves","year":"2017","unstructured":"Gon\u00e7alves VP, Giancristofaro GT, Geraldo Filho P, Johnson T, Carvalho V, Pessin G, de Almeida Neris VP, Ueyama J (2017) Assessing users\u2019 emotion at interaction time: a multimodal approach with multiple sensors. Soft Comput 21(18):5309\u20135323","journal-title":"Soft Comput"},{"key":"10249_CR15","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning. MIT press, Cambridge"},{"key":"10249_CR16","doi-asserted-by":"crossref","unstructured":"Han K, Yu D, Tashev I (2014) Speech emotion recognition using deep neural network and extreme learning machine. In: Fifteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2014-57"},{"key":"10249_CR17","doi-asserted-by":"publisher","first-page":"102974","DOI":"10.1016\/j.specom.2023.102974","volume":"154","author":"A Hashem","year":"2023","unstructured":"Hashem A, Arif M, Alghamdi M (2023) Speech emotion recognition approaches: A systematic review. Speech Commun 154:102974","journal-title":"Speech Commun"},{"key":"10249_CR18","doi-asserted-by":"publisher","first-page":"61672","DOI":"10.1109\/ACCESS.2020.2984368","volume":"8","author":"NH Ho","year":"2020","unstructured":"Ho NH, Yang HJ, Kim SH, Lee G (2020) Multimodal approach of speech emotion recognition using multi-level multi-head fusion attention-based recurrent neural network. IEEE Access 8:61672\u201361686","journal-title":"IEEE Access"},{"key":"10249_CR19","doi-asserted-by":"crossref","unstructured":"Huang KY, Wu CH, Hong QB, Su MH, Chen YH (2019) Speech emotion recognition using deep neural network considering verbal and nonverbal speech sounds. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5866\u20135870. IEEE","DOI":"10.1109\/ICASSP.2019.8682283"},{"issue":"3","key":"10249_CR20","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1080\/00401706.1991.10484833","volume":"33","author":"BH Juang","year":"1991","unstructured":"Juang BH, Rabiner LR (1991) Hidden markov models for speech recognition. Technometrics 33(3):251\u2013272","journal-title":"Technometrics"},{"key":"10249_CR21","doi-asserted-by":"crossref","unstructured":"Khurana S, Dev A, Bansal P (2024) Adam optimised human speech emotion recogniser based on statistical information distribution of chroma, mfcc, and mbse features. Multimedia Tools and Applications pp. 1\u201318","DOI":"10.1007\/s11042-024-19321-6"},{"issue":"4","key":"10249_CR22","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/BF00992553","volume":"5","author":"PR Kleinginna","year":"1981","unstructured":"Kleinginna PR, Kleinginna AM (1981) A categorized list of emotion definitions, with suggestions for a consensual definition. Motiv Emot 5(4):345\u2013379","journal-title":"Motiv Emot"},{"key":"10249_CR23","doi-asserted-by":"crossref","unstructured":"Kwon OW, Chan K, Hao J, Lee TW (2003) Emotion recognition by speech signals. In: Eighth European Conference on Speech Communication and Technology","DOI":"10.21437\/Eurospeech.2003-80"},{"issue":"1","key":"10249_CR24","first-page":"183","volume":"20","author":"S Kwon","year":"2020","unstructured":"Kwon S et al (2020) A cnn-assisted enhanced audio signal processing for speech emotion recognition. Sensors 20(1):183","journal-title":"Sensors"},{"key":"10249_CR25","doi-asserted-by":"publisher","first-page":"102156","DOI":"10.1016\/j.inffus.2023.102156","volume":"104","author":"C Li","year":"2024","unstructured":"Li C, Bian N, Zhao Z, Wang H, Schuller BW (2024) Multi-view domain-adaptive representation learning for eeg-based emotion recognition. Inf Fusion 104:102156","journal-title":"Inf Fusion"},{"key":"10249_CR26","doi-asserted-by":"crossref","unstructured":"Li R, Wang Y, Zheng WL, Lu BL (2022) A multi-view spectral-spatial-temporal masked autoencoder for decoding emotions with self-supervised learning. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 6\u201314","DOI":"10.1145\/3503161.3548243"},{"issue":"2","key":"10249_CR27","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s10772-021-09955-4","volume":"25","author":"M Liu","year":"2022","unstructured":"Liu M (2022) English speech emotion recognition method based on speech recognition. Int J Speech Tech 25(2):391\u2013398","journal-title":"Int J Speech Tech"},{"key":"10249_CR28","first-page":"1","volume":"24","author":"LY Mano","year":"2019","unstructured":"Mano LY, Fai\u00e7al BS, Gon\u00e7alves VP, Pessin G, Gomes PH, de Carvalho AC, Ueyama J (2019) An intelligent and generic approach for detecting human emotions: a case study with facial expressions. Soft Comput 24:1\u201313","journal-title":"Soft Comput"},{"issue":"2","key":"10249_CR29","first-page":"101","volume":"6","author":"Y Pan","year":"2012","unstructured":"Pan Y, Shen P, Shen L (2012) Speech emotion recognition using support vector machine. Int J Smart Home 6(2):101\u2013108","journal-title":"Int J Smart Home"},{"key":"10249_CR30","unstructured":"Picard RW (2000) Affective computing"},{"key":"10249_CR31","doi-asserted-by":"crossref","unstructured":"Purington A, Taft JG, Sannon S, Bazarova NN, Taylor SH (2017) \" alexa is my new bff\" social roles, user satisfaction, and personification of the amazon echo. In: Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems, pp. 2853\u20132859","DOI":"10.1145\/3027063.3053246"},{"issue":"6","key":"10249_CR32","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1037\/h0077714","volume":"39","author":"JA Russell","year":"1980","unstructured":"Russell JA (1980) A circumplex model of affect. J Pers Soc Psych 39(6):1161","journal-title":"J Pers Soc Psych"},{"issue":"5234","key":"10249_CR33","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1126\/science.270.5234.303","volume":"270","author":"RV Shannon","year":"1995","unstructured":"Shannon RV, Zeng FG, Kamath V, Wygonski J, Ekelid M (1995) Speech recognition with primarily temporal cues. Science 270(5234):303\u2013304","journal-title":"Science"},{"key":"10249_CR34","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.3844\/jcssp.2018.1420.1430","volume":"14","author":"J Torres Neto","year":"2018","unstructured":"Torres Neto J, Filho G, Mano L, Ueyama J (2018) Verbo: Voice emotion recognition database in portuguese language. J Comput Sci 14:1420\u20131430. https:\/\/doi.org\/10.3844\/jcssp.2018.1420.1430","journal-title":"J Comput Sci"},{"key":"10249_CR35","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 (2019) Speech emotion recognition using deep 1d and 2d cnn lstm networks. Biomed Signal Process Control 47:312\u2013323","journal-title":"Biomed Signal Process Control"},{"key":"10249_CR36","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.neunet.2021.03.013","volume":"141","author":"Z Zhao","year":"2021","unstructured":"Zhao Z, Li Q, Zhang Z, Cummins N, Wang H, Tao J, Schuller BW (2021) Combining a parallel 2d cnn with a self-attention dilated residual network for ctc-based discrete speech emotion recognition. Neural Netw 141:52\u201360","journal-title":"Neural Netw"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10249-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10249-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10249-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,28]],"date-time":"2024-09-28T08:03:44Z","timestamp":1727510624000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10249-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,9]]},"references-count":36,"journal-issue":{"issue":"32","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10249"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10249-4","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,9]]},"assertion":[{"value":"4 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}