{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T19:22:14Z","timestamp":1757704934665,"version":"3.40.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"26","license":[{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T00:00:00Z","timestamp":1680480000000},"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"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s11042-023-14648-y","type":"journal-article","created":{"date-parts":[[2023,4,3]],"date-time":"2023-04-03T10:01:28Z","timestamp":1680516088000},"page":"40839-40856","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Automated speech emotion polarization for a distance education system based on orbital local binary pattern and an appropriate sub-band selection technique"],"prefix":"10.1007","volume":"82","author":[{"given":"Dahiru","family":"Tanko","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fahrettin Burak","family":"Demir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9677-5684","authenticated-orcid":false,"given":"Sengul","family":"Dogan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sakir Engin","family":"Sahin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Turker","family":"Tuncer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,3]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Agarwal G, Om H (2021) Performance of deer hunting optimization based deep learning algorithm for speech emotion recognition. Multimed Tools Appl 80:9961-9992","key":"14648_CR1","DOI":"10.1007\/s11042-020-10118-x"},{"doi-asserted-by":"crossref","unstructured":"Aini Q, Budiarto M, Putra POH, Rahardja U (2020) Exploring E-learning challenges during the global COVID-19 pandemic: a review. Jurnal Sistem Informasi 16:57-65","key":"14648_CR2","DOI":"10.21609\/jsi.v16i2.1011"},{"doi-asserted-by":"crossref","unstructured":"Ancilin J, Milton A (2021) Improved speech emotion recognition with Mel frequency magnitude coefficient. Appl Acoust 179:108046","key":"14648_CR3","DOI":"10.1016\/j.apacoust.2021.108046"},{"doi-asserted-by":"crossref","unstructured":"Bandela SR, Kumar TK (2021) Unsupervised feature selection and NMF de-noising for robust Speech Emotion Recognition. Appl Acoust 172:107645","key":"14648_CR4","DOI":"10.1016\/j.apacoust.2020.107645"},{"doi-asserted-by":"crossref","unstructured":"Bastanfard A, Amirkhani D, Hasani M (n.d.) Increasing the accuracy of automatic speaker age estimation by using multiple UBMs. In: 2019 5th conference on knowledge based engineering and innovation (KBEI). IEEE, pp 592\u2013598","key":"14648_CR5","DOI":"10.1109\/KBEI.2019.8735005"},{"doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B (2005a) A database of German emotional speech. In: Interspeech. pp 1517\u20131520","key":"14648_CR6","DOI":"10.21437\/Interspeech.2005-446"},{"doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B (2005b) A database of German emotional speech. In: ninth European conference on speech communication and technology,Lissabon,Portugal, pp 1517\u20131520","key":"14648_CR7","DOI":"10.21437\/Interspeech.2005-446"},{"doi-asserted-by":"crossref","unstructured":"Busso C et al (2008) IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation 42:335","key":"14648_CR8","DOI":"10.1007\/s10579-008-9076-6"},{"doi-asserted-by":"crossref","unstructured":"Cahyadi A (2020) Covid-19 outbreak and new normal teaching in higher education: empirical resolve from Islamic Universities in Indonesia. Dinamika Ilmu 20:255-266","key":"14648_CR9","DOI":"10.21093\/di.v20i2.2545"},{"doi-asserted-by":"crossref","unstructured":"Chauhan K, Sharma KK, Varma T (2021) Speech emotion recognition using convolution neural networks. In: 2021 international conference on artificial intelligence and smart systems (ICAIS). IEEE, pp 1176\u20131181","key":"14648_CR10","DOI":"10.1109\/ICAIS50930.2021.9395844"},{"unstructured":"Costantini G, Iaderola I, Paoloni A, Todisco M (2014) EMOVO corpus: an Italian emotional speech database. In: International conference on language resources and evaluation (LREC 2014). European Language Resources Association (ELRA), pp 3501\u20133504","key":"14648_CR11"},{"unstructured":"Dupuis K, Pichora-Fuller MK (2011) Recognition of emotional speech for younger and older talkers: Behavioural findings from the toronto emotional speech set. Can Acoust 39:182\u2013183","key":"14648_CR12"},{"doi-asserted-by":"crossref","unstructured":"Fayek HM, Lech M, Cavedon L (2017) Evaluating deep learning architectures for Speech Emotion Recognition. Neural Netw 92:60\u201368","key":"14648_CR13","DOI":"10.1016\/j.neunet.2017.02.013"},{"doi-asserted-by":"crossref","unstructured":"Fonnegra RD, D\u00edaz GM (2018) Speech emotion recognition integrating paralinguistic features and auto-encoders in a deep learning model. In: International conference on human-computer interaction. Springer, pp 385\u2013396","key":"14648_CR14","DOI":"10.1007\/978-3-319-91238-7_31"},{"unstructured":"Goldberger J, Hinton GE, Roweis S, Salakhutdinov RR (2004) Neighbourhood components analysis Advances in neural information processing systems 17:513\u2013520","key":"14648_CR15"},{"doi-asserted-by":"crossref","unstructured":"Haq S, Jackson PJ (2010) In: Machine audition: principles, algorithms and systems. In: Multimodal Emotion Recognition. IGI Global ch., Hershey PA, pp 398\u2013423","key":"14648_CR16","DOI":"10.4018\/978-1-61520-919-4.ch017"},{"doi-asserted-by":"crossref","unstructured":"Ilyas O (2021) Pseudo-colored rate map representation for speech emotion recognition. Biomed Signal Process Control 66:102502","key":"14648_CR17","DOI":"10.1016\/j.bspc.2021.102502"},{"doi-asserted-by":"crossref","unstructured":"Issa D, Demirci MF, Yazici A (2020) Speech emotion recognition with deep convolutional neural networks. Biomed Signal Process Control 59:101894","key":"14648_CR18","DOI":"10.1016\/j.bspc.2020.101894"},{"doi-asserted-by":"crossref","unstructured":"Jing S, Mao X, Chen L (2018) Prominence features: Effective emotional features for speech emotion recognition. Digit Signal Proc 72:216\u2013231","key":"14648_CR19","DOI":"10.1016\/j.dsp.2017.10.016"},{"doi-asserted-by":"crossref","unstructured":"Kalhor E, Bakhtiari B (2021) Speaker independent feature selection for speech emotion recognition: a multitask approach. Multimed Tools Appl 80:8127\u20138146","key":"14648_CR20","DOI":"10.1007\/s11042-020-10119-w"},{"doi-asserted-by":"crossref","unstructured":"Kambalimath S, Deka PC (2021) Performance enhancement of SVM model using discrete wavelet transform for daily streamflow forecasting. Environ Earth Sci 80:1\u201316","key":"14648_CR21","DOI":"10.1007\/s12665-021-09394-z"},{"doi-asserted-by":"crossref","unstructured":"Kwon S (2021) MLT-DNet: Speech emotion recognition using 1D dilated CNN based on multi-learning trick approach. Expert Syst Appl 167:114177","key":"14648_CR22","DOI":"10.1016\/j.eswa.2020.114177"},{"doi-asserted-by":"crossref","unstructured":"Latif S, Qayyum A, Usman M, Qadir J (2018) Cross lingual speech emotion recognition: Urdu vs. western languages. In: 2018 international conference on frontiers of information technology (FIT). IEEE, pp 88\u201393","key":"14648_CR23","DOI":"10.1109\/FIT.2018.00023"},{"doi-asserted-by":"crossref","unstructured":"Li M et al (2021) Contrastive unsupervised learning for speech emotion recognition arXiv preprint arXiv:210206357","key":"14648_CR24","DOI":"10.1109\/ICASSP39728.2021.9413910"},{"doi-asserted-by":"crossref","unstructured":"Liu Z-T, Rehman A, Wu M, Cao W-H, Hao M (2021) Speech emotion recognition based on formant characteristics feature extraction and phoneme type convergence. Inf Sci 563:309\u2013325","key":"14648_CR25","DOI":"10.1016\/j.ins.2021.02.016"},{"key":"14648_CR26","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone SR, Russo FA (2018) 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:e0196391","journal-title":"PLoS ONE"},{"doi-asserted-by":"crossref","unstructured":"Mao Q, Dong M, Huang Z, Zhan Y (2014) Learning salient features for speech emotion recognition using convolutional neural networks. IEEE Trans Multimed 16:2203\u20132213","key":"14648_CR27","DOI":"10.1109\/TMM.2014.2360798"},{"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). IEEE, pp 8\u20138","key":"14648_CR28","DOI":"10.1109\/ICDEW.2006.145"},{"doi-asserted-by":"crossref","unstructured":"Meyer P, Xu Z, Fingscheidt T (2021) Improving Convolutional Recurrent Neural Networks for Speech Emotion Recognition. In: 2021 IEEE spoken language technology workshop (SLT). IEEE, pp 365\u2013372","key":"14648_CR29","DOI":"10.1109\/SLT48900.2021.9383513"},{"doi-asserted-by":"crossref","unstructured":"Mirsamadi S, Barsoum E, Zhang C (2017) Automatic speech emotion recognition using recurrent neural networks with local attention. In: 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2227\u20132231","key":"14648_CR30","DOI":"10.1109\/ICASSP.2017.7952552"},{"doi-asserted-by":"crossref","unstructured":"Mohamad Nezami O, Jamshid Lou P, Karami M (2019) ShEMO: a large-scale validated database for Persian speech emotion detection. Lang Resour Eval 53:1\u201316","key":"14648_CR31","DOI":"10.1007\/s10579-018-9427-x"},{"unstructured":"Pan Y, Shen P, Shen L (2012) Speech emotion recognition using support vector machine. Int J Smart Home 6:101\u2013108","key":"14648_CR32"},{"doi-asserted-by":"crossref","unstructured":"Pawar MD, Kokate RD (2021) Convolution neural network based automatic speech emotion recognition using Mel-frequency Cepstrum coefficients. Multimed Tools Appl 80:15563\u201315587","key":"14648_CR33","DOI":"10.1007\/s11042-020-10329-2"},{"doi-asserted-by":"crossref","unstructured":"Pham H-H, Ho T-T-H (2020) Toward a \u2018new normal\u2019with e-learning in Vietnamese higher education during the post COVID-19 pandemic. High Educ Res Dev 39:1327-1331","key":"14648_CR34","DOI":"10.1080\/07294360.2020.1823945"},{"doi-asserted-by":"crossref","unstructured":"Ramakrishnan S, El Emary IM (2013) Speech emotion recognition approaches in human computer interaction. Telecommun Syst 52:1467\u20131478","key":"14648_CR35","DOI":"10.1007\/s11235-011-9624-z"},{"unstructured":"Savargiv M, Bastanfard A (2014) Study on unit-selection and statistical parametric speech synthesis techniques. J Comput Robot 7:19\u201325","key":"14648_CR36"},{"doi-asserted-by":"crossref","unstructured":"Savargiv M, Bastanfard A (2016) Real-time speech emotion recognition by minimum number of features. In: 2016 Artificial intelligence and robotics (IRANOPEN). IEEE, pp 72\u201376","key":"14648_CR37","DOI":"10.1109\/RIOS.2016.7529493"},{"doi-asserted-by":"crossref","unstructured":"Seo J, Lee B (2022) Multi-task conformer with multi-feature combination for speech emotion recognition. Symmetry 14:1428","key":"14648_CR38","DOI":"10.3390\/sym14071428"},{"doi-asserted-by":"crossref","unstructured":"Sun P, Lu X, Xu C, Sun W, Pan B (2020) Understanding of COVID-19 based on current evidence. J Med. Virol 92:548-551","key":"14648_CR39","DOI":"10.1002\/jmv.25722"},{"doi-asserted-by":"crossref","unstructured":"Torrence C, Compo GP (1998) A practical guide to wavelet analysis. Bull Amer Meteor Soc 79:61\u201378","key":"14648_CR40","DOI":"10.1175\/1520-0477(1998)079<0061:APGTWA>2.0.CO;2"},{"doi-asserted-by":"crossref","unstructured":"Triyason T, Tassanaviboon A, Kanthamanon P (2020) Hybrid classroom: designing for the new normal after COVID-19 pandemic. In: Proceedings of the 11th international conference on advances in information technology, pp 1\u20138","key":"14648_CR41","DOI":"10.1145\/3406601.3406635"},{"doi-asserted-by":"crossref","unstructured":"Tuncer T, Dogan S, Acharya UR (2021) Automated accurate speech emotion recognition system using twine shuffle pattern and iterative neighborhood component analysis techniques. Knowl Based Syst 211:106547","key":"14648_CR42","DOI":"10.1016\/j.knosys.2020.106547"},{"doi-asserted-by":"crossref","unstructured":"Tzirakis P, Zhang J, Schuller BW (2018) End-to-end speech emotion recognition using deep neural networks. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 5089\u20135093","key":"14648_CR43","DOI":"10.1109\/ICASSP.2018.8462677"},{"doi-asserted-by":"crossref","unstructured":"Vapnik V (1998) The support vector method of function estimation. In: Nonlinear modeling. Springer, pp 55\u201385","key":"14648_CR44","DOI":"10.1007\/978-1-4615-5703-6_3"},{"unstructured":"Vapnik V (2013) The nature of statistical learning theory. Springer Science & Business Media","key":"14648_CR45"},{"doi-asserted-by":"crossref","unstructured":"Wani TM, Gunawan TS, Qadri SAA, Kartiwi M, Ambikairajah E (2021) A comprehensive review of speech emotion recognition systems. IEEE Access 9:47795\u201347814","key":"14648_CR46","DOI":"10.1109\/ACCESS.2021.3068045"},{"doi-asserted-by":"crossref","unstructured":"Yildirim S, Kaya Y, K\u0131l\u0131\u00e7 F (2021) A modified feature selection method based on metaheuristic algorithms for speech emotion recognition. Appl Acoust 173:107721","key":"14648_CR47","DOI":"10.1016\/j.apacoust.2020.107721"},{"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","key":"14648_CR48","DOI":"10.3389\/fphys.2021.643202"},{"doi-asserted-by":"crossref","unstructured":"Zhao J, Mao X, Chen L (2019) Speech emotion recognition using deep 1D & 2D CNN LSTM networks. Biomed Signal Process Control 47:312-323","key":"14648_CR49","DOI":"10.1016\/j.bspc.2018.08.035"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14648-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14648-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14648-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T15:43:59Z","timestamp":1744213439000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14648-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,3]]},"references-count":49,"journal-issue":{"issue":"26","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["14648"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14648-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,4,3]]},"assertion":[{"value":"15 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors of this manuscript declare no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}