{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:58:47Z","timestamp":1780937927481,"version":"3.54.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100014786","name":"Northern Border University","doi-asserted-by":"publisher","award":["NBU-FPEJ-2026-2932-04"],"award-info":[{"award-number":["NBU-FPEJ-2026-2932-04"]}],"id":[{"id":"10.13039\/501100014786","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020912","name":"King Faisal University","doi-asserted-by":"publisher","award":["ORF-2026-417"],"award-info":[{"award-number":["ORF-2026-417"]}],"id":[{"id":"10.13039\/501100020912","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020912","name":"King Faisal University","doi-asserted-by":"publisher","award":["KFU261582"],"award-info":[{"award-number":["KFU261582"]}],"id":[{"id":"10.13039\/501100020912","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023674","name":"Deanship of Scientific Research, King Khalid University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023674","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004242","name":"Princess Nourah Bint Abdulrahman University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004242","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007446","name":"King Khalid University","doi-asserted-by":"publisher","award":["RGP2\/247\/46"],"award-info":[{"award-number":["RGP2\/247\/46"]}],"id":[{"id":"10.13039\/501100007446","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020247","name":"University of Bisha","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020247","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002383","name":"King Saud University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002383","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.eswa.2026.132213","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:04:25Z","timestamp":1774368265000},"page":"132213","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Automated speech emotion recognition model using feature-driven ensemble deep learning and puma optimization algorithm"],"prefix":"10.1016","volume":"321","author":[{"given":"Abeer S.","family":"Almogren","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghreed Ali","family":"Alsudais","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nouf J.","family":"Aljohani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed Burhanur","family":"Rehman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faten","family":"Derouez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Basim","family":"Alamri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali M.","family":"Al-Sharafi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1357-2819","authenticated-orcid":false,"given":"Somia A.","family":"Asklany","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132213_b0005","doi-asserted-by":"crossref","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","article-title":"Speech recognition using deep neural networks: A systematic review","volume":"7","author":"Nassif","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132213_b0010","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1007\/s11831-019-09344-w","article-title":"A survey of deep learning and its applications: A new paradigm to machine learning","volume":"27","author":"Dargan","year":"2020","journal-title":"Archives of Computational Methods in Engineering"},{"issue":"3","key":"10.1016\/j.eswa.2026.132213_b0015","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1007\/s11831-021-09647-x","article-title":"Survey on machine learning in speech emotion recognition and vision systems using a recurrent neural network (RNN)","volume":"29","author":"Yadav","year":"2022","journal-title":"Archives of Computational Methods in Engineering"},{"issue":"1","key":"10.1016\/j.eswa.2026.132213_b0020","article-title":"English speech recognition and evaluation of pronunciation quality using deep learning","volume":"2022","author":"Xu","year":"2022","journal-title":"Mobile Information Systems"},{"key":"10.1016\/j.eswa.2026.132213_b0025","doi-asserted-by":"crossref","first-page":"117327","DOI":"10.1109\/ACCESS.2019.2936124","article-title":"Speech emotion recognition using deep learning techniques: A review","volume":"7","author":"Khalil","year":"2019","journal-title":"IEEE Access"},{"issue":"5","key":"10.1016\/j.eswa.2026.132213_b0030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3178115","article-title":"Deep learning for environmentally robust speech recognition: An overview of recent developments","volume":"9","author":"Zhang","year":"2018","journal-title":"ACM Transactions on Intelligent Systems and Technology"},{"key":"10.1016\/j.eswa.2026.132213_b0035","doi-asserted-by":"crossref","first-page":"204951","DOI":"10.1109\/ACCESS.2020.3037073","article-title":"A framework for hate speech detection using deep convolutional neural network","volume":"8","author":"Roy","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132213_b0040","series-title":"2019 International Seminar on Application for Technology of Information and Communication (iSemantic)","first-page":"251","article-title":"Javanese gender speech recognition using deep learning and singular value decomposition","author":"Nugroho","year":"2019"},{"key":"10.1016\/j.eswa.2026.132213_b0045","doi-asserted-by":"crossref","first-page":"72","DOI":"10.54216\/JISIoT.010202","article-title":"Handling within-word and cross-word pronunciation variation for Arabic speech recognition (knowledge-based approach)","volume":"1","author":"El-Henawy","year":"2020","journal-title":"Journal of Intelligent Systems and Internet of Things"},{"issue":"2","key":"10.1016\/j.eswa.2026.132213_b0050","first-page":"57","article-title":"Facial expression recognition with gender identification","volume":"2","author":"Gupta","year":"2021","journal-title":"Full-Length Article"},{"key":"10.1016\/j.eswa.2026.132213_b0055","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.ijcce.2024.11.008","article-title":"Speech emotion recognition algorithm of intelligent robot based on ACO-SVM","volume":"6","author":"Kang","year":"2025","journal-title":"International Journal of Cognitive Computing in Engineering"},{"key":"10.1016\/j.eswa.2026.132213_b0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128711","article-title":"ESERNet: Learning spectrogram structure relationship for effective speech emotion recognition with Swin Transformer in classroom discourse analysis","volume":"612","author":"Liu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.eswa.2026.132213_b0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2024.106912","article-title":"FMLAN: A novel framework for cross-subject and cross-session EEG emotion recognition","volume":"100","author":"Yu","year":"2025","journal-title":"Biomedical Signal Processing and Control"},{"issue":"1","key":"10.1016\/j.eswa.2026.132213_b0070","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.13376","article-title":"Facial emotion recognition using convolutional neural network-based krill head optimization","volume":"42","author":"Devi","year":"2025","journal-title":"Expert Systems"},{"key":"10.1016\/j.eswa.2026.132213_b0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122946","article-title":"MSER: Multimodal speech emotion recognition using cross-attention with deep fusion","volume":"245","author":"Khan","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.132213_b0080","article-title":"Speech emotion recognition using extreme machine learning","volume":"10","author":"Koti","year":"2024","journal-title":"EAI Endorsed Transactions on Internet of Things"},{"key":"10.1016\/j.eswa.2026.132213_b0085","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2023.3297269","article-title":"Lightweight deep learning framework for speech emotion recognition","author":"Akinpelu","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132213_b0090","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.specom.2022.11.005","article-title":"Modulation spectral features for speech emotion recognition using deep neural networks","volume":"146","author":"Singh","year":"2023","journal-title":"Speech Communication"},{"issue":"2","key":"10.1016\/j.eswa.2026.132213_b0095","first-page":"213","article-title":"A novel multi-task and ensembled optimized parallel convolutional autoencoder and transformer for speech emotion recognition","volume":"56","author":"Sharifzadeh Jafari","year":"2024","journal-title":"AUT Journal of Electrical Engineering"},{"issue":"2","key":"10.1016\/j.eswa.2026.132213_b0100","doi-asserted-by":"crossref","DOI":"10.32604\/cmc.2024.059382","article-title":"Enhancing user experience in AI-powered human\u2013computer communication with vocal emotions identification using a novel deep learning method","volume":"82","author":"Alhussen","year":"2025","journal-title":"Computers, Materials & Continua"},{"key":"10.1016\/j.eswa.2026.132213_b0105","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113223","article-title":"Cluster search optimization of deep neural networks for audio emotion classification","volume":"314","author":"Slade","year":"2025","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.132213_b0110","doi-asserted-by":"crossref","DOI":"10.1016\/j.icte.2025.04.007","article-title":"TMNet: Transformer-fused multimodal framework for emotion recognition via EEG and speech","author":"Alam","year":"2025","journal-title":"ICT Express"},{"key":"10.1016\/j.eswa.2026.132213_b0115","article-title":"XEmoAccent: Embracing diversity in cross-accent emotion recognition using deep learning","author":"Ahmad","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.eswa.2026.132213_b0120","doi-asserted-by":"crossref","DOI":"10.1016\/j.jiixd.2025.02.004","article-title":"Multimodal emotion recognition method in complex dynamic scenes","author":"Liu","year":"2025","journal-title":"Journal of Information and Intelligence"},{"issue":"36","key":"10.1016\/j.eswa.2026.132213_b0125","doi-asserted-by":"crossref","first-page":"83963","DOI":"10.1007\/s11042-024-19017-x","article-title":"Effective MLP and CNN based ensemble learning for speech emotion recognition","volume":"83","author":"Middya","year":"2024","journal-title":"Multimedia Tools and Applications"},{"key":"10.1016\/j.eswa.2026.132213_b0130","doi-asserted-by":"crossref","unstructured":"Deepa, P., Khilar, R., & Mohapatra, S. K. (2025). Advancements in Parkinson's disease diagnosis through automated speech analysis. In Wellness Management Powered by AI Technologies (pp. 173\u2013205).","DOI":"10.1002\/9781394287024.ch7"},{"issue":"3","key":"10.1016\/j.eswa.2026.132213_b0135","doi-asserted-by":"crossref","DOI":"10.3390\/a17030090","article-title":"Optimizing speech emotion recognition with deep learning and Grey Wolf Optimization: A multi-dataset approach","volume":"17","author":"Tyagi","year":"2024","journal-title":"Algorithms"},{"issue":"18","key":"10.1016\/j.eswa.2026.132213_b0140","doi-asserted-by":"crossref","first-page":"54331","DOI":"10.1007\/s11042-023-17097-9","article-title":"Optimal trained ensemble of classification model for speech emotion recognition: Considering cross-lingual and multi-lingual scenarios","volume":"83","author":"Kawade","year":"2024","journal-title":"Multimedia Tools and Applications"},{"issue":"11","key":"10.1016\/j.eswa.2026.132213_b0145","doi-asserted-by":"crossref","first-page":"7397","DOI":"10.1109\/TVCG.2024.3456213","article-title":"Expressive 3D facial animation generation based on local-to-global latent diffusion","volume":"30","author":"Song","year":"2024","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"10.1016\/j.eswa.2026.132213_b0150","doi-asserted-by":"crossref","first-page":"5944","DOI":"10.1109\/TASE.2024.3434610","article-title":"Grasping with occlusion-aware ally method in complex scenes","volume":"22","author":"Li","year":"2025","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"6","key":"10.1016\/j.eswa.2026.132213_b0155","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-021-0236-9","article-title":"ResLNet: Deep residual LSTM network with longer input for action recognition","volume":"16","author":"Wang","year":"2022","journal-title":"Frontiers of Computer Science"},{"key":"10.1016\/j.eswa.2026.132213_b0160","doi-asserted-by":"crossref","unstructured":"Huang, F., Bei, Y., Yang, Z., Jiang, J., Chen, H., Shen, Q., & Yu, P. S. (2025). Large language model simulator for cold-start recommendation. In Proceedings of the WSDM '25 (pp. xx\u2013xx). New York, NY, USA.","DOI":"10.1145\/3701551.3703546"},{"issue":"1","key":"10.1016\/j.eswa.2026.132213_b0165","article-title":"Automatic stutter speech recognition and classification using hyper-heuristic search algorithm","volume":"14","author":"Grandhi","year":"2024","journal-title":"International Journal of Automation and Smart Technology"},{"issue":"1","key":"10.1016\/j.eswa.2026.132213_b0170","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.jksuci.2017.06.006","article-title":"A new homomorphic and method noise thresholding based despeckling of SAR image using anisotropic diffusion","volume":"32","author":"Singh","year":"2020","journal-title":"Journal of King Saud University-Computer and Information Sciences"},{"key":"10.1016\/j.eswa.2026.132213_b0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2019.107050","article-title":"Performance analysis of multiple aggregated acoustic features for environment sound classification","volume":"158","author":"Su","year":"2020","journal-title":"Applied Acoustics"},{"issue":"6","key":"10.1016\/j.eswa.2026.132213_b0180","doi-asserted-by":"crossref","first-page":"835","DOI":"10.22247\/ijcna\/2024\/50","article-title":"DDoS attack detection in cloud computing using optimized Elman neural network based on bacterial colony optimization and centroid opposition-based learning","volume":"11","author":"Kalvikkarasi","year":"2024","journal-title":"International Journal of Computer Networks and Applications (IJCNA)"},{"issue":"12","key":"10.1016\/j.eswa.2026.132213_b0185","doi-asserted-by":"crossref","first-page":"6022","DOI":"10.2166\/wcc.2024.719","article-title":"Integrated machine learning models for enhancing tropical rainfall prediction using NASA POWER meteorological data","volume":"15","author":"Saleh","year":"2024","journal-title":"Journal of Water and Climate Change"},{"issue":"1","key":"10.1016\/j.eswa.2026.132213_b0190","doi-asserted-by":"crossref","first-page":"309","DOI":"10.32604\/cmc.2024.053538","article-title":"Sports events recognition using multi features and deep belief network","volume":"81","author":"Alabdullah","year":"2024","journal-title":"Computers, Materials & Continua"},{"key":"10.1016\/j.eswa.2026.132213_b0195","article-title":"Puma algorithm for environmental emissions and generation costs minimization dispatch in power systems","volume":"e02547","author":"Al Faiya","year":"2025","journal-title":"Scientific African"},{"key":"10.1016\/j.eswa.2026.132213_b0200","unstructured":"https:\/\/www.kaggle.com\/datasets\/piyushagni5\/berlin-dataset-of-emotional-speech-emodb."},{"key":"10.1016\/j.eswa.2026.132213_b0205","unstructured":"https:\/\/www.kaggle.com\/datasets\/uwrfkaggler\/ravdess-emotional-speech-audio."},{"issue":"4","key":"10.1016\/j.eswa.2026.132213_b0210","doi-asserted-by":"crossref","DOI":"10.3390\/sym13040697","article-title":"Machine-learning based memory prediction model for data parallel workloads in Apache Spark","volume":"13","author":"Myung","year":"2021","journal-title":"Symmetry"},{"issue":"16","key":"10.1016\/j.eswa.2026.132213_b0215","doi-asserted-by":"crossref","DOI":"10.3390\/app13169222","article-title":"Inference latency prediction approaches using statistical information for object detection in edge computing","volume":"13","author":"Kong","year":"2023","journal-title":"Applied Sciences"},{"key":"10.1016\/j.eswa.2026.132213_b0220","article-title":"Towards robust speech emotion recognition and classification using natural language processing with deep learning model","author":"Alahmari","year":"2024","journal-title":"Fractals"},{"key":"10.1016\/j.eswa.2026.132213_b0225","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2023.3321122","article-title":"Mel-MViTv2: Enhanced speech emotion recognition with Mel spectrogram and improved multiscale vision transformers","author":"Ong","year":"2023","journal-title":"IEEE Access"},{"issue":"10","key":"10.1016\/j.eswa.2026.132213_b0230","doi-asserted-by":"crossref","DOI":"10.3390\/electronics10101163","article-title":"A review on speech emotion recognition using deep learning and attention mechanism","volume":"10","author":"Lieskovsk\u00e1","year":"2021","journal-title":"Electronics"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011267?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011267?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T16:07:54Z","timestamp":1780934874000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426011267"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":46,"alternative-id":["S0957417426011267"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132213","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Automated speech emotion recognition model using feature-driven ensemble deep learning and puma optimization algorithm","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132213","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132213"}}