{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T07:30:28Z","timestamp":1765870228502,"version":"3.48.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"39","license":[{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"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":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-025-20956-2","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T06:16:13Z","timestamp":1754374573000},"page":"48071-48098","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An approach to accurate recognition of emotions through speech-to-image signal conversion and deep convolutional neural networks"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1548-9190","authenticated-orcid":false,"given":"Mohammad Reza","family":"Falahzadeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yazdan","family":"ZandiyeVakili","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Harimi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edris","family":"Zaman Farsa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arash","family":"Ahmadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ajith","family":"Abraham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"key":"20956_CR1","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.asoc.2018.05.018","volume":"70","author":"A Garcia-Garcia","year":"2018","unstructured":"Garcia-Garcia A, Orts-Escolano S, Oprea S, Villena-Martinez V, Martinez P, Garcia-Rodriguez J (2018) A survey on deep learning techniques for image and video semantic segmentation. Appl Soft Comput 70:41\u201365","journal-title":"Appl Soft Comput"},{"key":"20956_CR2","doi-asserted-by":"publisher","first-page":"139489","DOI":"10.1109\/ACCESS.2021.3118541","volume":"9","author":"V Sharma","year":"2021","unstructured":"Sharma V, Gupta M, Kumar A, Mishra D (2021) Video Processing Using Deep Learning Techniques: A systematic literature review. IEEE Access 9:139489\u2013139507","journal-title":"IEEE Access"},{"issue":"6","key":"20956_CR3","doi-asserted-by":"publisher","first-page":"2806","DOI":"10.1109\/TPAMI.2020.3045007","volume":"44","author":"S Oprea","year":"2022","unstructured":"Oprea S et al (2022) A review on deep learning techniques for video prediction. IEEE Trans Pattern Anal Mach Intell 44(6):2806\u20132826","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20956_CR4","doi-asserted-by":"publisher","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","volume":"7","author":"AB Nassif","year":"2019","unstructured":"Nassif AB, Shahin I, Attili I, Azzeh M, Shaalan K (2019) Speech recognition using deep neural networks: a systematic review. IEEE Access 7:19143\u201319165","journal-title":"IEEE Access"},{"key":"20956_CR5","doi-asserted-by":"crossref","unstructured":"Mehrish A, Majumder N, Bharadwaj R, Mihalcea R, Poria S (2023) A review of deep learning techniques for speech processing. Inform Fusion 99. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S1566253523001859","DOI":"10.1016\/j.inffus.2023.101869"},{"key":"20956_CR6","doi-asserted-by":"publisher","first-page":"172231","DOI":"10.1109\/ACCESS.2019.2956508","volume":"7","author":"L Jiao","year":"2019","unstructured":"Jiao L, Zhao J (2019) A survey on the new generation of deep learning in image processing. IEEE Access 7:172231\u2013172263","journal-title":"IEEE Access"},{"issue":"9","key":"20956_CR7","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","volume":"26","author":"KH Jin","year":"2017","unstructured":"Jin KH, McCann MT, Froustey E, Unser M (2017) Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process 26(9):4509\u20134522","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"20956_CR8","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/TSMC.2020.3018325","volume":"51","author":"AI K\u00e1roly","year":"2021","unstructured":"K\u00e1roly AI, Galambos P, Kuti J, Rudas IJ (2021) Deep learning in robotics: survey on model structures and training strategies. IEEE Trans Syst Man Cybern: Syst 51(1):266\u2013279","journal-title":"IEEE Trans Syst Man Cybern: Syst"},{"key":"20956_CR9","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"20956_CR10","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. Available: http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"20956_CR11","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, pp 2818\u20132826. https:\/\/ieeexplore.ieee.org\/document\/7780677","DOI":"10.1109\/CVPR.2016.308"},{"key":"20956_CR12","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, pp 770\u2013778. https:\/\/ieeexplore.ieee.org\/document\/7780459?denied=","DOI":"10.1109\/CVPR.2016.90"},{"key":"20956_CR13","doi-asserted-by":"publisher","first-page":"117327","DOI":"10.1109\/ACCESS.2019.2936124","volume":"7","author":"RA Khalil","year":"2019","unstructured":"Khalil RA, Jones E, Babar MI, Jan T, Zafar MH, Alhussain T (2019) Speech Emotion Recognition Using Deep Learning Techniques: A Review. IEEE Access 7:117327\u2013117345","journal-title":"IEEE Access"},{"key":"20956_CR14","doi-asserted-by":"crossref","unstructured":"Lieskovska E, Jakubec M, Jarina R, Chmulik M (2021) A review on speech emotion recognition using deep learning and attention mechanism. Electronics 10. https:\/\/www.mdpi.com\/2079-9292\/10\/10\/1163","DOI":"10.3390\/electronics10101163"},{"issue":"6","key":"20956_CR15","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1109\/TMM.2017.2766843","volume":"20","author":"S Zhang","year":"2018","unstructured":"Zhang S, Zhang S, Huang T, Gao W (2018) Speech Emotion Recognition Using Deep Convolutional Neural Network and Discriminant Temporal Pyramid Matching. IEEE Trans Multimed 20(6):1576\u20131590","journal-title":"IEEE Trans Multimed"},{"issue":"6","key":"20956_CR16","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1049\/iet-spr.2017.0320","volume":"12","author":"J Zhao","year":"2018","unstructured":"Zhao J, Mao X, Chen L (2018) Learning deep features to recognise speech emotion using merged deep CNN. IET Signal Proc 12(6):713\u2013721","journal-title":"IET Signal Proc"},{"issue":"10","key":"20956_CR17","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 (2018) 3-D Convolutional Recurrent Neural Networks With Attention Model for Speech Emotion Recognition. IEEE Signal Process Lett 25(10):1440\u20131444","journal-title":"IEEE Signal Process Lett"},{"key":"20956_CR18","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 & 2D CNN LSTM networks. Biomed Signal Process Control 47:312\u2013323","journal-title":"Biomed Signal Process Control"},{"issue":"11","key":"20956_CR19","doi-asserted-by":"publisher","first-page":"1675","DOI":"10.1109\/TASLP.2019.2925934","volume":"27","author":"Y Xie","year":"2019","unstructured":"Xie Y, Liang R, Liang Z, Huang C, Zou C, Schuller B (2019) Speech Emotion Classification Using Attention-Based LSTM. IEEE\/ACM Trans Audio, Speech, Lang Process 27(11):1675\u20131685","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"key":"20956_CR20","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 MF, Yazici A (2020) Speech emotion recognition with deep convolutional neural networks. Biomed Signal Process Control 59:101894","journal-title":"Biomed Signal Process Control"},{"key":"20956_CR21","doi-asserted-by":"publisher","first-page":"106889","DOI":"10.1109\/ACCESS.2020.3000751","volume":"8","author":"H Zhao","year":"2020","unstructured":"Zhao H, Xiao Y, Zhang Z (2020) Robust Semisupervised Generative Adversarial Networks for Speech Emotion Recognition via Distribution Smoothness. IEEE Access 8:106889\u2013106900","journal-title":"IEEE Access"},{"key":"20956_CR22","doi-asserted-by":"crossref","unstructured":"Zhang H, Gou R, Shang J, Shen F, Wu Y, Dai G (2021) Pre-trained deep convolution neural network model with attention for speech emotion recognition. Front Physiol 12. https:\/\/www.frontiersin.org\/journals\/physiology\/articles\/10.3389\/fphys.2021.643202\/full","DOI":"10.3389\/fphys.2021.643202"},{"key":"20956_CR23","doi-asserted-by":"crossref","unstructured":"Atila O, \u015eeng\u00fcr A (2021) Attention guided 3D CNN-LSTM model for accurate speech based emotion recognition. Appl Acoust 182. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0003682X21003546","DOI":"10.1016\/j.apacoust.2021.108260"},{"key":"20956_CR24","doi-asserted-by":"publisher","first-page":"59860","DOI":"10.1109\/ACCESS.2021.3073234","volume":"9","author":"L Yang","year":"2021","unstructured":"Yang L, Xie K, Wen C, He J-B (2021) Speech Emotion Analysis of Netizens Based on Bidirectional LSTM and PGCDBN. IEEE Access 9:59860\u201359872","journal-title":"IEEE Access"},{"key":"20956_CR25","doi-asserted-by":"publisher","first-page":"5332","DOI":"10.1109\/ACCESS.2020.3047395","volume":"9","author":"H Zhang","year":"2021","unstructured":"Zhang H, Huang H, Han H (2021) Attention-Based Convolution Skip Bidirectional Long Short-Term Memory Network for Speech Emotion Recognition. IEEE Access 9:5332\u20135342","journal-title":"IEEE Access"},{"key":"20956_CR26","doi-asserted-by":"crossref","unstructured":"Li D, Liu J, Yang Z, Sun L, Wang Z (2021) Speech emotion recognition using recurrent neural networks with directional self attention. Expert Syst Appl 173. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S095741742100124X","DOI":"10.1016\/j.eswa.2021.114683"},{"key":"20956_CR27","doi-asserted-by":"publisher","first-page":"112460","DOI":"10.1109\/ACCESS.2022.3217226","volume":"10","author":"MR Falahzadeh","year":"2022","unstructured":"Falahzadeh MR, Farsa EZ, Harimi A, Ahmadi A, Abraham A (2022) 3D Convolutional Neural Network for Speech Emotion Recognition With Its Realization on Intel CPU and NVIDIA GPU. IEEE Access 10:112460\u2013112471","journal-title":"IEEE Access"},{"key":"20956_CR28","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.specom.2022.02.007","volume":"139","author":"A Bakhshi","year":"2022","unstructured":"Bakhshi A, Harimi A, Chalup S (2022) CyTex: transforming speech to textured images for speech emotion recognition. Speech Commun 139:62\u201375","journal-title":"Speech Commun"},{"key":"20956_CR29","doi-asserted-by":"publisher","first-page":"49265","DOI":"10.1109\/ACCESS.2022.3172954","volume":"10","author":"AA Abdelhamid","year":"2022","unstructured":"Abdelhamid AA et al (2022) Robust speech emotion recognition using CNN\u2009+\u2009LSTM based on stochastic fractal search optimization algorithm. IEEE Access 10:49265\u201349284","journal-title":"IEEE Access"},{"issue":"2","key":"20956_CR30","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1109\/TAFFC.2019.2947464","volume":"13","author":"S Zhang","year":"2022","unstructured":"Zhang S, Zhao X, Tian Q (2022) Spontaneous speech emotion recognition using multiscale deep convolutional LSTM. IEEE Trans Affect Comput 13(2):680\u2013688","journal-title":"IEEE Trans Affect Comput"},{"issue":"4","key":"20956_CR31","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1109\/TCDS.2021.3123979","volume":"14","author":"P Jiang","year":"2022","unstructured":"Jiang P, Xu X, Tao H, Zhao L, Zou C (2022) Convolutional-Recurrent Neural Networks With Multiple Attention Mechanisms for Speech Emotion Recognition. IEEE Trans Cogn Dev Syst 14(4):1564\u20131573","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"20956_CR32","doi-asserted-by":"publisher","first-page":"122302","DOI":"10.1109\/ACCESS.2022.3223705","volume":"10","author":"S Kakuba","year":"2022","unstructured":"Kakuba S, Poulose A, Han DS (2022) Attention-Based Multi-Learning Approach for Speech Emotion Recognition With Dilated Convolution. IEEE Access 10:122302\u2013122313","journal-title":"IEEE Access"},{"key":"20956_CR33","doi-asserted-by":"publisher","first-page":"36018","DOI":"10.1109\/ACCESS.2022.3163856","volume":"10","author":"F Andayani","year":"2022","unstructured":"Andayani F, Theng LB, Tsun MT, Chua C (2022) Hybrid LSTM-Transformer Model for Emotion Recognition From Speech Audio Files. IEEE Access 10:36018\u201336027","journal-title":"IEEE Access"},{"issue":"1","key":"20956_CR34","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TNNLS.2020.3027600","volume":"33","author":"L Yi","year":"2022","unstructured":"Yi L, Mak M-W (2022) Improving Speech Emotion Recognition With Adversarial Data Augmentation Network. IEEE Trans Neural Netw Learn Syst 33(1):172\u2013184","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"20956_CR35","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1109\/TASLP.2023.3277291","volume":"31","author":"A Dutt","year":"2023","unstructured":"Dutt A, Gader P (2023) Wavelet Multiresolution Analysis Based Speech Emotion Recognition System Using 1D CNN LSTM Networks. IEEE\/ACM Trans Audio, Speech, Lang Process 31:2043\u20132054","journal-title":"IEEE\/ACM Trans Audio, Speech, Lang Process"},{"key":"20956_CR36","doi-asserted-by":"crossref","unstructured":"Sun C, Li H, Ma L (2023) Speech emotion recognition based on improved masking EMD and convolutional recurrent neural network. Front Psychol 13. https:\/\/www.frontiersin.org\/journals\/psychology\/articles\/10.3389\/fpsyg.2022.1075624\/full","DOI":"10.3389\/fpsyg.2022.1075624"},{"key":"20956_CR37","doi-asserted-by":"crossref","unstructured":"Pan J, Fang W, Zhang Z, Chen B, Zhang Z, Wang S (2024) Multimodal emotion recognition based on facial expressions, speech, and EEG. IEEE Open J Eng Med Biol 5:396\u2013403. https:\/\/ieeexplore.ieee.org\/document\/10026861","DOI":"10.1109\/OJEMB.2023.3240280"},{"key":"20956_CR38","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/s00034-022-02130-3","volume":"42","author":"MR Falahzadeh","year":"2023","unstructured":"Falahzadeh MR, Farokhi F, Harimi A, Sabbaghi-Nadooshan R (2023) Deep convolutional neural network and Gray Wolf optimization algorithm for speech emotion recognition. Circuits Syst Signal Process 42:449\u2013492","journal-title":"Circuits Syst Signal Process"},{"key":"20956_CR39","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.patrec.2020.05.002","volume":"135","author":"R John Wesley","year":"2020","unstructured":"John Wesley R, Nayeemulla Khan A, Shahina A (2020) Phoneme classification in reconstructed phase space with convolutional neural networks. Pattern Recogn Lett 135:299\u2013306","journal-title":"Pattern Recogn Lett"},{"issue":"4","key":"20956_CR40","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1109\/TSA.2005.848885","volume":"13","author":"MT Johnson","year":"2005","unstructured":"Johnson MT, Povinelli RJ, Lindgren AC, Ye J, Liu X, Indrebo KM (2005) Time-domain isolated phoneme classification using reconstructed phase spaces,. IEEE Trans Speech Audio Process 13(4):458\u2013466","journal-title":"IEEE Trans Speech Audio Process"},{"issue":"6","key":"20956_CR41","doi-asserted-by":"publisher","first-page":"2178","DOI":"10.1109\/TSP.2006.873479","volume":"54","author":"RJ Povinelli","year":"2006","unstructured":"Povinelli RJ, Johnson MT, Lindgren AC, Roberts FM, Ye J (2006) Statistical models of reconstructed phase spaces for signal classification. IEEE Trans Signal Process 54(6):2178\u20132186","journal-title":"IEEE Trans Signal Process"},{"key":"20956_CR42","doi-asserted-by":"publisher","first-page":"1679","DOI":"10.3389\/fpsyg.2018.01679","volume":"9","author":"S Wallot","year":"2018","unstructured":"Wallot S, M\u00f8nster D (2018) Calculation of Average Mutual Information (AMI) and False-Nearest Neighbors (FNN) for the Estimation of Embedding Parameters of Multidimensional Time Series in Matlab. Front Psychol 9:1679","journal-title":"Front Psychol"},{"key":"20956_CR43","doi-asserted-by":"crossref","unstructured":"Cho J et al (2018) Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling. In: 2018 IEEE Spoken Language Technology Workshop (SLT), Athens, Greece, pp 521\u2013527. https:\/\/ieeexplore.ieee.org\/abstract\/document\/8639655","DOI":"10.1109\/SLT.2018.8639655"},{"issue":"2","key":"20956_CR44","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1109\/TAFFC.2021.3135152","volume":"14","author":"M Gerczuk","year":"2023","unstructured":"Gerczuk M, Amiriparian S, Ottl S, Schuller BW (2023) EmoNet: A Transfer Learning Framework for Multi-Corpus Speech Emotion Recognition. IEEE Trans Affect Comput 14(2):1472\u20131487","journal-title":"IEEE Trans Affect Comput"},{"key":"20956_CR45","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B (2005) A database of German emotional speech. In: Proc. Interspeech, pp 1517\u20131520. https:\/\/www.researchgate.net\/profile\/Felix-Burkhardt-2\/publication\/221491017_A_database_of_German_emotional_speech\/links\/00b7d5226f45d66e38000000\/A-database-of-German-emotional-speech.pdf"},{"key":"20956_CR46","doi-asserted-by":"crossref","unstructured":"Martin O, Kotsia I, Macq B, Pitas I (2006) The eNTERFACE' 05 audio-visual emotion database. In: 22nd International Conference on Data Engineering Workshops (ICDEW'06), Atlanta, GA, pp 1\u20138. https:\/\/ieeexplore.ieee.org\/abstract\/document\/1623803","DOI":"10.1109\/ICDEW.2006.145"},{"key":"20956_CR47","doi-asserted-by":"crossref","unstructured":"Gursesli MC, Lombardi S, Duradoni M, Bocchi L, Guazzini A, Lanata A (2024) Facial emotion recognition (FER) through custom lightweight CNN model: Performance evaluation in public datasets. IEEE Access 12:45543\u201345559. https:\/\/ieeexplore.ieee.org\/document\/10477992","DOI":"10.1109\/ACCESS.2024.3380847"},{"key":"20956_CR48","doi-asserted-by":"crossref","unstructured":"Hou Z et al (2024) EEG-based emotion recognition with EERN model. In: 2024 9th International Conference on Intelligent Computing and Signal Processing (ICSP), Xian, pp 830\u2013834. https:\/\/ieeexplore.ieee.org\/document\/10743301","DOI":"10.1109\/ICSP62122.2024.10743301"},{"key":"20956_CR49","doi-asserted-by":"crossref","unstructured":"Schuller B, Vlasenko B, Eyben F, Rigoll G, Wendemuth A (2009) Acoustic emotion recognition: A benchmark comparison of performances. In: 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, Moreno, pp 552\u2013557. https:\/\/ieeexplore.ieee.org\/document\/5372886","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"20956_CR50","doi-asserted-by":"publisher","first-page":"77086","DOI":"10.1109\/ACCESS.2023.3297269","volume":"11","author":"S Akinpelu","year":"2023","unstructured":"Akinpelu S, Viriri S, Adegun A (2023) Lightweight Deep Learning Framework for Speech Emotion Recognition. IEEE Access 11:77086\u201377098","journal-title":"IEEE Access"},{"key":"20956_CR51","doi-asserted-by":"crossref","unstructured":"Islam MMM et al (2024) Enhancing speech emotion recognition using deep convolutional neural networks. In: ICMLT 2024: Proceedings of the 2024 9th International Conference on Machine Learning Technologies, pp 95\u2013100. https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3674029.3674045","DOI":"10.1145\/3674029.3674045"},{"issue":"49","key":"20956_CR52","first-page":"1","volume":"58","author":"C Barhoumi","year":"2025","unstructured":"Barhoumi C, BenAyed Y (2025) Real-time speech emotion recognition using deep learning and data augmentation. Artif Intell Rev 58(49):1\u201341","journal-title":"Artif Intell Rev"},{"key":"20956_CR53","doi-asserted-by":"publisher","first-page":"75557","DOI":"10.1007\/s11042-024-18316-7","volume":"83","author":"WA Khan","year":"2024","unstructured":"Khan WA et al (2024) Speech emotion recognition using feature fusion: a hybrid approach to deep learning. Multimed Tools Appl 83:75557\u201375584","journal-title":"Multimed Tools Appl"},{"key":"20956_CR54","doi-asserted-by":"publisher","first-page":"116638","DOI":"10.1109\/ACCESS.2023.3326071","volume":"11","author":"FAD R\u00ed","year":"2023","unstructured":"R\u00ed FAD, Ciardi FC, Conci N (2023) Speech Emotion Recognition and Deep Learning: An Extensive Validation Using Convolutional Neural Networks. IEEE Access 11:116638\u2013116649","journal-title":"IEEE Access"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20956-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-025-20956-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-025-20956-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T07:26:09Z","timestamp":1765869969000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-025-20956-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":54,"journal-issue":{"issue":"39","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["20956"],"URL":"https:\/\/doi.org\/10.1007\/s11042-025-20956-2","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2025,8,5]]},"assertion":[{"value":"22 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}