{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:55:19Z","timestamp":1752231319731},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"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":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-023-02358-z","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T09:02:13Z","timestamp":1700125333000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning Algorithms for Speech Emotion Recognition with Hybrid Spectral Features"],"prefix":"10.1007","volume":"5","author":[{"given":"Raghu","family":"Kogila","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manchala","family":"Sadanandam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanumanthu","family":"Bhukya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"2358_CR1","unstructured":"Sujatha B, Ameena O. Speech emotion recognition using HMM, GMM and SVM models. IJPRES VI(3). 2016."},{"key":"2358_CR2","doi-asserted-by":"crossref","first-page":"311","DOI":"10.7763\/IJET.2016.V8.904","volume":"8","author":"M Selvaraj","year":"2016","unstructured":"Selvaraj M, Bhuvana R, Padmaja S. Human speech emotion recognition. Int J Eng Technol. 2016;8:311\u201323.","journal-title":"Int J Eng Technol"},{"key":"2358_CR3","doi-asserted-by":"publisher","unstructured":"Kurpukdee N, Koriyama T, Kobayashi T, Kasuriya S, Wutiwiwatchai C, Lamsrichan P. Speech emotion recognition using convolutional long short-term memory neural network and support vector machines. In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1744\u20131749. 2017. https:\/\/doi.org\/10.1109\/APSIPA.2017.8282315.","DOI":"10.1109\/APSIPA.2017.8282315"},{"key":"2358_CR4","first-page":"175","volume":"2","author":"K Leila","year":"2018","unstructured":"Leila K, Youssef S, Mohamed M, Kosai R, Mohamed AM. Speech emotion recognition: methods and cases study. Int Conf Agents Artif Intell (ICAART 2018). 2018;2:175\u201382 (ISBN:978-989-758-275-2).","journal-title":"Int Conf Agents Artif Intell (ICAART 2018)"},{"key":"2358_CR5","doi-asserted-by":"crossref","unstructured":"Manamela PJ, Manamela MJ, et.al. The automatic recognition of sepedi speech emotions based on machine learning algorithms. IEEE. 2018.","DOI":"10.1109\/ICABCD.2018.8465403"},{"key":"2358_CR6","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. Speech emotion recognition using deep convolutional neural network and discriminant temporal pyramid matching. IEEE Trans Multimed. 2018;20:1576\u201390.","journal-title":"IEEE Trans Multimed"},{"key":"2358_CR7","doi-asserted-by":"publisher","unstructured":"Apoorv S, Kshitij KS, Harini M (2020) Speech emotion recognition using convolutional neural network (CNN). Int J Psychosoc Rehabilit. https:\/\/doi.org\/10.37200\/IJPR\/V24I8\/PR280260.","DOI":"10.37200\/IJPR\/V24I8\/PR280260"},{"key":"2358_CR8","unstructured":"Anusha K, Himabindu V, Anil B. Feature Extraction Algorithms to improve the speech emotion recognition rate. Int J Speech Technol. 2020."},{"key":"2358_CR9","doi-asserted-by":"publisher","unstructured":"Hadhami A, Yassine BA. Speech emotion recognition with deep learning. In: 24th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems. 2020. https:\/\/doi.org\/10.1016\/j.procs.2020.08.027.","DOI":"10.1016\/j.procs.2020.08.027"},{"issue":"2","key":"2358_CR10","first-page":"101","volume":"6","author":"Y Pan","year":"2021","unstructured":"Pan Y, Shen P, Shen L. Speech emotion recognition using support vector machine. Int J Smart Home. 2021;6(2):101\u20138.","journal-title":"Int J Smart Home"},{"key":"2358_CR11","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s00138-022-01294-x","volume":"33","author":"R Jahangir","year":"2022","unstructured":"Jahangir R, Teh YW, Mujtaba G, Alroobaea R, Shaikh ZH, Ali I. Convolutional neural network-based cross-corpus speech emotion recognition with data augmentation and features fusion. Mach Vis Appl. 2022;33:41.","journal-title":"Mach Vis Appl"},{"key":"2358_CR12","doi-asserted-by":"publisher","first-page":"4897","DOI":"10.1007\/s11042-021-10553-4","volume":"81","author":"C Wang","year":"2022","unstructured":"Wang C, Ren Y, Zhang N, Cui F, Luo S. Speech emotion recognition based on multi-feature and multi-lingual fusion. Multimed Tools Appl. 2022;81:4897\u2013907. https:\/\/doi.org\/10.1007\/s11042-021-10553-4.","journal-title":"Multimed Tools Appl"},{"key":"2358_CR13","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. Speech emotion recognition through hybrid features and convolutional neural network. Appl Sci. 2023;13:4750. https:\/\/doi.org\/10.3390\/app13084750.","journal-title":"Appl Sci."},{"key":"2358_CR14","doi-asserted-by":"publisher","unstructured":"Chawki B, Yassine BA. Real-time speech emotion recognition using deep learning and data augmentation. PREPRINT (Version 1). 2023. https:\/\/doi.org\/10.21203\/rs.3.rs-2874039\/v1.","DOI":"10.21203\/rs.3.rs-2874039\/v1"},{"key":"2358_CR15","unstructured":"Fundamentals of Speech Recognition, Pearson Edition."},{"key":"2358_CR16","doi-asserted-by":"crossref","unstructured":"Koolagudi SG, Maity S, Kumar VA, Chakrabati S, Rao KS (2009) IITKGP-SESC: Speech database for emotion analysis. Commun Comput Inform Sci. LNCS, 485\u2013492.","DOI":"10.1007\/978-3-642-03547-0_46"},{"issue":"1","key":"2358_CR17","first-page":"9","volume":"54","author":"N Singh","year":"2012","unstructured":"Singh N, Khan RA, Shree R. MFCC and prosodic feature extraction techniques: a comparative study. Int J Comput Appl (0975\u20138887). 2012;54(1):9\u201313.","journal-title":"Int J Comput Appl (0975\u20138887)"},{"key":"2358_CR18","unstructured":"Huang X, Acero A, Hon H-W, Foreword B-RR. Spoken language processing: a guide to theory, algorithm, and system development. Prentice Hall. 2001."},{"issue":"4","key":"2358_CR19","first-page":"2023","volume":"101","author":"K Raghu","year":"2023","unstructured":"Raghu K, Sadanandam M. Speech emotion recognition system performance analysis with optimized features using different classification algorithms. JATIT J Theor Appl Inform Technol. 2023;101(4):2023.","journal-title":"JATIT J Theor Appl Inform Technol."},{"key":"2358_CR20","doi-asserted-by":"publisher","DOI":"10.11113\/jt.v78.6925","author":"I Idrisa","year":"2015","unstructured":"Idrisa I, Salamb MS, Sunarc MS. Speech emotion classification using Svm and Mlp on prosodic and voice quality features. Jurnal Teknologi. 2015. https:\/\/doi.org\/10.11113\/jt.v78.6925.","journal-title":"Jurnal Teknologi"},{"key":"2358_CR21","unstructured":"Pao T, Chen Y, Yeh J, Li P. Mandarin emotional speech recognition based on SVM and NN. In: Paper presented on 2006 at 18th International Conference on Pattern Recognition (ICPR\u201906), (1, pp. 1096\u20131100). 2006."},{"key":"2358_CR22","unstructured":"Peete\u2019s G. Chroma-based estimation of musical key from audio-signal analysis. In: Proceedings of the 7th International Conference on Music Information Retrieval, Victoria. 2006."},{"key":"2358_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894","author":"D Issa","year":"2020","unstructured":"Issa D, Demirci MF, Yazici A. Speech emotion recognition with deep convolutional neural networks. Biomed Signal Process Control. 2020. https:\/\/doi.org\/10.1016\/j.bspc.2020.101894.","journal-title":"Biomed Signal Process Control."},{"key":"2358_CR24","unstructured":"Alif BAQ, Asiful A, Celia S. Convolutional Neural Network based Speech Emotion Recognition. In: 2019 IEEE International Conference onSignal Processing, Information, Communication and Systems (SPICSCON). 2019."},{"key":"#cr-split#-2358_CR25.1","doi-asserted-by":"crossref","unstructured":"Huang Z, Dong M, Mao Q, Zhan Y. Speech emotion recognition using CNN. In: Proceedings of the 22nd ACM international conference on Multimedia, Orlando, FL, USA, 3-7 November 2014","DOI":"10.1145\/2647868.2654984"},{"key":"#cr-split#-2358_CR25.2","unstructured":"Association for Computing Machinery: New York, NY, USA, pp. 801-804. 2014."},{"key":"2358_CR26","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1109\/TASLP.2021.3133196","volume":"30","author":"M Hou","year":"2022","unstructured":"Hou M, Zhang Z, Cao Q, Zhang D, Lu G. Multi-view speech emotion recognition via collective relation construction. IEEE\/ACM Transact Audio Speech Lang Process. 2022;30:218\u201329. https:\/\/doi.org\/10.1109\/TASLP.2021.3133196.","journal-title":"IEEE\/ACM Transact Audio Speech Lang Process"},{"key":"2358_CR27","unstructured":"Livingstone S, Peck K, Russo F (2012) RAVDESS: the ryerson audio-visual database of emotional speech and song. In: Proceedings of the 22nd annual meeting of the Canadian Society for Brain, Behaviour and Cognitive Science (CSBBCS), Canada."},{"key":"2358_CR28","unstructured":"Ganga Mohan P, Kishore Kumar B, Rambabu B, Gangashetty SV. IIIT-H TEMD semi-natural emotional speech database from professional actors and non-actors. In: Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 1538\u20131545."},{"key":"2358_CR29","doi-asserted-by":"crossref","unstructured":"Gangamohan P, Reddy Kadiri S, Yegnanarayana B. Analysis of emotional speech at subsegmental level, INTERSPEECH 2013, Lyon. 2013","DOI":"10.21437\/Interspeech.2013-20"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02358-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-023-02358-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02358-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T09:03:45Z","timestamp":1700125425000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-023-02358-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,16]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1]]}},"alternative-id":["2358"],"URL":"https:\/\/doi.org\/10.1007\/s42979-023-02358-z","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,16]]},"assertion":[{"value":"22 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2023","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"}}],"article-number":"17"}}