{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T03:37:24Z","timestamp":1783049844495,"version":"3.54.6"},"reference-count":61,"publisher":"Springer Science and Business Media LLC","issue":"36","license":[{"start":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T00:00:00Z","timestamp":1712102400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T00:00:00Z","timestamp":1712102400000},"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\/s11042-024-19017-x","type":"journal-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T08:02:26Z","timestamp":1712131346000},"page":"83963-83990","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Effective MLP and CNN based ensemble learning for speech emotion recognition"],"prefix":"10.1007","volume":"83","author":[{"given":"Asif Iqbal","family":"Middya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baibhav","family":"Nag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7598-8266","authenticated-orcid":false,"given":"Sarbani","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,4,3]]},"reference":[{"key":"19017_CR1","doi-asserted-by":"crossref","unstructured":"Trigeorgis G, Ringeval F, Brueckner R, Marchi E, Nicolaou MA, Schuller B, Zafeiriou S (2016)\u201cAdieu features? end-to-end speech emotion recognition using a deep convolutional recurrent network,\u201d in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5200\u20135204","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"19017_CR2","doi-asserted-by":"crossref","unstructured":"Li X, Tao J, Johnson MT, Soltis J, Savage A, Leong KM, Newman JD (2007) \u201cStress and emotion classification using jitter and shimmer features,\u201d in 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP\u201907, vol 4. IEEE, pp IV\u20131081","DOI":"10.1109\/ICASSP.2007.367261"},{"key":"19017_CR3","doi-asserted-by":"crossref","unstructured":"Chen CH, Lu PT, Chen OTC (2010) \u201cClassification of four affective modes in online songs and speeches,\u201d in The 19th Annual Wireless and Optical Communications Conference (WOCC 2010). IEEE, pp 1\u20134","DOI":"10.1109\/WOCC.2010.5510629"},{"issue":"4","key":"19017_CR4","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/TASL.2008.2009578","volume":"17","author":"C Busso","year":"2009","unstructured":"Busso C, Lee S, Narayanan S (2009) Analysis of emotionally salient aspects of fundamental frequency for emotion detection. IEEE Transactions on Audio, Speech, lang process 17(4):582\u2013596","journal-title":"IEEE Transactions on Audio, Speech, lang process"},{"issue":"5","key":"19017_CR5","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu S, Falk TH, Chan WY (2011) Automatic speech emotion recognition using modulation spectral features. Speech Comm 53(5):768\u2013785","journal-title":"Speech Comm"},{"key":"19017_CR6","doi-asserted-by":"crossref","unstructured":"Rieger SA, Muraleedharan R, Ramachandran RP (2014) \u201cSpeech based emotion recognition using spectral feature extraction and an ensemble of knn classifiers,\u201d in The 9th International Symposium on Chinese Spoken Language Processing. IEEE, pp 589\u2013593","DOI":"10.1109\/ISCSLP.2014.6936711"},{"key":"19017_CR7","doi-asserted-by":"crossref","unstructured":"Mittal S, Agarwal S, Nigam MJ, (2018) \u201cReal time multiple face recognition: A deep learning approach,\u201d in Proceedings of the 2018 International Conference on Digital Medicine and Image Processing, pp 70\u201376","DOI":"10.1145\/3299852.3299853"},{"key":"19017_CR8","doi-asserted-by":"crossref","unstructured":"Huang KY, Wu C-H, Hong Q-B, Su M-H, Chen Y-H (2019) \u201cSpeech emotion recognition using deep neural network considering verbal and nonverbal speech sounds,\u201d in ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5866\u20135870","DOI":"10.1109\/ICASSP.2019.8682283"},{"key":"19017_CR9","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) \u201cDeep residual learning for image recognition,\u201d in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"19017_CR10","doi-asserted-by":"crossref","unstructured":"Bae H-S, Lee H-J, Lee S-G (2016) \u201cVoice recognition based on adaptive mfcc and deep learning,\u201d in 2016 IEEE 11th Conference on Industrial Electronics and Applications (ICIEA), pp 1542\u20131546","DOI":"10.1109\/ICIEA.2016.7603830"},{"key":"19017_CR11","doi-asserted-by":"crossref","unstructured":"Lim W, Jang D, Lee T (2016) \u201cSpeech emotion recognition using convolutional and recurrent neural networks,\u201d in 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp 1\u20134","DOI":"10.1109\/APSIPA.2016.7820699"},{"issue":"5","key":"19017_CR12","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(5):e0196391","journal-title":"PloS One"},{"key":"19017_CR13","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B , (2005) \u201cA database of german emotional speech,\u201d in Ninth European Conference on Speech Communication and Technology","DOI":"10.21437\/Interspeech.2005-446"},{"key":"19017_CR14","unstructured":"Haq S-u (2011) Audio visual expressed emotion classification. University of Surrey (United Kingdom)"},{"key":"19017_CR15","unstructured":"Pichora-Fuller MK, Dupuis K (2020) \u201cToronto emotional speech set (TESS),\u201d [Online]. Available: https:\/\/doi.org\/10.5683\/SP2\/E8H2MF"},{"key":"19017_CR16","doi-asserted-by":"crossref","unstructured":"Shegokar P, Sircar P (2016) \u201cContinuous wavelet transform based speech emotion recognition,\u201d in 2016 10th International Conference on Signal Processing and Communication Systems (ICSPCS). IEEE, pp 1\u20138","DOI":"10.1109\/ICSPCS.2016.7843306"},{"issue":"3","key":"19017_CR17","doi-asserted-by":"publisher","first-page":"3705","DOI":"10.1007\/s11042-017-5539-3","volume":"78","author":"Y Zeng","year":"2019","unstructured":"Zeng Y, Mao H, Peng D, Yi Z (2019) Spectrogram based multi-task audio classification. Multimed Tools Appl 78(3):3705\u20133722","journal-title":"Multimed Tools Appl"},{"key":"19017_CR18","doi-asserted-by":"crossref","unstructured":"Popova AS, Rassadin AG, Ponomarenko AA (2017) \u201cEmotion recognition in sound,\u201d in International Conference on Neuroinformatics. Springer, pp 117\u2013124","DOI":"10.1007\/978-3-319-66604-4_18"},{"key":"19017_CR19","doi-asserted-by":"crossref","unstructured":"Liu Z-T, Xie Q, Wu M, Cao W-H, Mei Y, Mao J-W (2018)\u201cSpeech emotion recognition based on an improved brain emotion learning model,\u201d Neurocomputing, 309 pp 145\u2013156","DOI":"10.1016\/j.neucom.2018.05.005"},{"key":"19017_CR20","doi-asserted-by":"crossref","unstructured":"Hajarolasvadi N Demirel H (2019) \u201c3d cnn-based speech emotion recognition using k-means clustering and spectrograms,\u201d ntropy, 21(5):479","DOI":"10.3390\/e21050479"},{"key":"19017_CR21","unstructured":"Padi S, Manocha D, Sriram RD (2020) \u201cMulti-window data augmentation approach for speech emotion recognition,\u201d arxiv:2010.09895"},{"issue":"1","key":"19017_CR22","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/TCE.2021.3056421","volume":"67","author":"R Chatterjee","year":"2021","unstructured":"Chatterjee R, Mazumdar S, Sherratt RS, Halder R, Maitra T, Giri D (2021) Real-time speech emotion analysis for smart home assistants. IEEE Trans. Consum Electron 67(1):68\u201376","journal-title":"IEEE Trans. Consum Electron"},{"key":"19017_CR23","doi-asserted-by":"crossref","unstructured":"Dolka H Juliet S (2021) \u201cSpeech emotion recognition using ann on mfcc features,\u201d in 2021 3rd International Conference on Signal Processing and Communication (ICPSC). IEEE, pp 431\u2013435","DOI":"10.1109\/ICSPC51351.2021.9451810"},{"key":"19017_CR24","doi-asserted-by":"crossref","unstructured":"Iqbal MZ (2020)\u201cMfcc and machine learning based speech emotion recognition over tess and iemocap datasets,\u201d Foundation University Journal of Engineering and Applied Science (FUJEAS), 1(2):pp 25\u201330","DOI":"10.33897\/fujeas.v1i2.321"},{"issue":"8","key":"19017_CR25","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s00521-016-2712-y","volume":"29","author":"S Demircan","year":"2018","unstructured":"Demircan S, Kahramanli H (2018) Application of fuzzy c-means clustering algorithm to spectral features for emotion classification from speech. Neural Comput Appl 29(8):59\u201366","journal-title":"Neural Comput Appl"},{"key":"19017_CR26","doi-asserted-by":"crossref","unstructured":"Issa D, Demirci MF Yazici A (2020)\u201cSpeech emotion recognition with deep convolutional neural networks,\u201d Biomedical Signal Processing and Control, 59 p 101894","DOI":"10.1016\/j.bspc.2020.101894"},{"key":"19017_CR27","doi-asserted-by":"crossref","unstructured":"Badshah AM, Ahmad J, Rahim N, Baik SW (2017)\u201cSpeech emotion recognition from spectrograms with deep convolutional neural network,\u201d in 2017 International Conference on Platform Technology and Service (PlatCon), pp 1\u20135","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"19017_CR28","doi-asserted-by":"crossref","unstructured":"Lampropoulos AS Tsihrintzis GA (2012) \u201cEvaluation of mpeg-7 descriptors for speech emotional recognition,\u201d in 2012 Eighth International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp 98\u2013101","DOI":"10.1109\/IIH-MSP.2012.29"},{"issue":"1","key":"19017_CR29","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/TAFFC.2015.2392101","volume":"6","author":"K Wang","year":"2015","unstructured":"Wang K, An N, Li BN, Zhang Y, Li L (2015) Speech emotion recognition using fourier parameters. IEEE Trans Affect Comput 6(1):69\u201375","journal-title":"IEEE Trans Affect Comput"},{"key":"19017_CR30","doi-asserted-by":"crossref","unstructured":"Ververidis D Kotropoulos C (2005)\u201cEmotional speech classification using gaussian mixture models and the sequential floating forward selection algorithm,\u201d in 2005 IEEE International Conference on Multimedia and Expo. IEEE, pp 1500\u20131503","DOI":"10.1109\/ICME.2005.1521717"},{"key":"19017_CR31","doi-asserted-by":"crossref","unstructured":"Nwe TL, Foo SW, De\u00a0Silva LC (2003)\u201cSpeech emotion recognition using hidden markov models,\u201d Speech communication, 41(4) pp 603\u2013623","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"19017_CR32","doi-asserted-by":"crossref","unstructured":"Triantafyllopoulos A, Keren G, Wagner J, Steiner I, Schuller BW (2019) \u201cTowards Robust Speech Emotion Recognition Using Deep Residual Networks for Speech Enhancement,\u201d in Proc. Interspeech 2019, pp 1691\u20131695. [Online]. Available: http:\/\/dx.doi.org\/10.21437\/Interspeech.2019-1811","DOI":"10.21437\/Interspeech.2019-1811"},{"key":"19017_CR33","doi-asserted-by":"crossref","unstructured":"Mustaqeem, Kwon S (2021)\u201cAtt-net: Enhanced emotion recognition system using lightweight self-attention module,\u201d Applied Soft Computing, vol 102. p 107101. [Online]. Available: http:\/\/dx.doi.org\/10.1016\/j.asoc.2021.107101","DOI":"10.1016\/j.asoc.2021.107101"},{"key":"19017_CR34","doi-asserted-by":"crossref","unstructured":"\u201cClstm: Deep feature-based speech emotion recognition using the hierarchical convlstm network,\u201d (2020) Mathematics, 8(12): p 2133 [Online]. Available: http:\/\/dx.doi.org\/10.3390\/math8122133","DOI":"10.3390\/math8122133"},{"key":"19017_CR35","doi-asserted-by":"crossref","unstructured":"\u201cMlt-dnet: Speech emotion recognition using 1d dilated cnn based on multi-learning trick approach,\u201d (2021) Expert Systems with Applications, vol 167. p 114177 [Online]. Available: http:\/\/dx.doi.org\/10.1016\/j.eswa.2020.114177","DOI":"10.1016\/j.eswa.2020.114177"},{"key":"19017_CR36","doi-asserted-by":"crossref","unstructured":"Zhao J, Mao X, Chen L (2019)\u201cSpeech emotion recognition using deep 1d & 2d cnn lstm networks,\u201d Biomedical Signal Processing and Control, 47 pp 312\u2013323","DOI":"10.1016\/j.bspc.2018.08.035"},{"key":"19017_CR37","doi-asserted-by":"crossref","unstructured":"Chatziagapi A, Paraskevopoulos G, Sgouropoulos D, Pantazopoulos G, Nikandrou M, Giannakopoulos T, Katsamanis A, Potamianos A, Narayanan S (2019) \u201cData Augmentation Using GANs for Speech Emotion Recognition,\u201d in Proc. Interspeech 2019, pp. 171\u2013175. [Online]. Available: http:\/\/dx.doi.org\/10.21437\/Interspeech.2019-2561","DOI":"10.21437\/Interspeech.2019-2561"},{"issue":"1\u20132","key":"19017_CR38","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/S0167-6393(02)00070-5","volume":"40","author":"E Douglas-Cowie","year":"2003","unstructured":"Douglas-Cowie E, Campbell N, Cowie R, Roach P (2003) Emotional speech: Towards a new generation of databases. Speech Comm 40(1\u20132):33\u201360","journal-title":"Speech Comm"},{"key":"19017_CR39","doi-asserted-by":"crossref","unstructured":"Huang Z, Dong M, Mao Q, Zhan Y (2014) \u201cSpeech emotion recognition using cnn,\u201d in Proceedings of the 22nd ACM international conference on Multimedia, pp 801\u2013804","DOI":"10.1145\/2647868.2654984"},{"issue":"2","key":"19017_CR40","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.specom.2006.11.004","volume":"49","author":"D Morrison","year":"2007","unstructured":"Morrison D, Wang R, De Silva LC (2007) Ensemble methods for spoken emotion recognition in call-centres. Speech Comm 49(2):98\u2013112","journal-title":"Speech Comm"},{"issue":"3","key":"19017_CR41","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.csl.2010.10.001","volume":"25","author":"EM Albornoz","year":"2011","unstructured":"Albornoz EM, Milone DH, Rufiner HL (2011) Spoken emotion recognition using hierarchical classifiers. Comput Speech Lang 25(3):556\u2013570","journal-title":"Comput Speech Lang"},{"key":"19017_CR42","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.neunet.2023.03.026","volume":"163","author":"F Daneshfar","year":"2023","unstructured":"Daneshfar F, Jamshidi MB (2023) An octonion-based nonlinear echo state network for speech emotion recognition in metaverse. Neural Netw 163:108\u2013121","journal-title":"Neural Netw"},{"key":"19017_CR43","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":"19017_CR44","doi-asserted-by":"crossref","unstructured":"Morais E, Hoory R, Zhu W, Gat I, Damasceno M, Aronowitz H (2022)\u201cSpeech emotion recognition using self-supervised features,\u201d in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 6922\u20136926","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"19017_CR45","doi-asserted-by":"publisher","first-page":"2180","DOI":"10.1016\/j.matpr.2021.12.246","volume":"57","author":"N Senthilkumar","year":"2022","unstructured":"Senthilkumar N, Karpakam S, Devi MG, Balakumaresan R, Dhilipkumar P (2022) Speech emotion recognition based on bi-directional lstm architecture and deep belief networks. Mater Today Proc 57:2180\u20132184","journal-title":"Mater Today Proc"},{"key":"19017_CR46","doi-asserted-by":"crossref","unstructured":"Aftab A, Morsali A, Ghaemmaghami S, Champagne B (2022) \u201cLight-sernet: A lightweight fully convolutional neural network for speech emotion recognition,\u201d in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 6912\u20136916","DOI":"10.1109\/ICASSP43922.2022.9746679"},{"key":"19017_CR47","doi-asserted-by":"crossref","unstructured":"Tzirakis P, Nguyen A, Zafeiriou S, Schuller BW (2021)\u201cSpeech emotion recognition using semantic information,\u201d in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 6279\u20136283","DOI":"10.1109\/ICASSP39728.2021.9414866"},{"key":"19017_CR48","doi-asserted-by":"crossref","unstructured":"Huijuan Z, Ning Y, Ruchuan W (2021)\u201cCoarse-to-fine speech emotion recognition based on multi-task learning,\u201d Journal of Signal Processing Systems, 93(2): pp 299\u2013308","DOI":"10.1007\/s11265-020-01538-x"},{"key":"19017_CR49","doi-asserted-by":"crossref","unstructured":"Neumann M, Vu NT (2017) \u201cAttentive convolutional neural network based speech emotion recognition: A study on the impact of input features, signal length, and acted speech,\u201d arXiv preprint arxiv:1706.00612","DOI":"10.21437\/Interspeech.2017-917"},{"issue":"8","key":"19017_CR50","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","volume":"11","author":"P Tzirakis","year":"2017","unstructured":"Tzirakis P, Trigeorgis G, Nicolaou MA, Schuller BW, Zafeiriou S (2017) End-to-end multimodal emotion recognition using deep neural networks. IEEE J Sel Top in Sig Process 11(8):1301\u20131309","journal-title":"IEEE J Sel Top in Sig Process"},{"issue":"3","key":"19017_CR51","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1121\/1.1915893","volume":"8","author":"SS Stevens","year":"1937","unstructured":"Stevens SS, Volkmann J, Newman EB (1937) A scale for the measurement of the psychological magnitude pitch. J Acoust Soc Am 8(3):185\u2013190","journal-title":"J Acoust Soc Am"},{"issue":"3","key":"19017_CR52","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/S0167-6393(98)00019-3","volume":"24","author":"Y Soon","year":"1998","unstructured":"Soon Y, Koh SN, Yeo CK (1998) Noisy speech enhancement using discrete cosine transform. Speech Comm 24(3):249\u2013257","journal-title":"Speech Comm"},{"key":"19017_CR53","doi-asserted-by":"crossref","unstructured":"Beigi H (2011)\u201cSpeaker recognition,\u201d in Fundamentals of Speaker Recognition. Springer, pp 543\u2013559","DOI":"10.1007\/978-0-387-77592-0_17"},{"key":"19017_CR54","unstructured":"Wakefield GH (1999)\u201cChromagram visualization of the singing voice,\u201d in International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications"},{"key":"19017_CR55","unstructured":"McFee B, Metsai A, McVicar M, Balke S, Thom\u00e9 C, Raffel C, Zalkow F, Malek A, Dana, Lee K, Nieto O, Ellis D, Mason J, Battenberg E, Seyfarth S, Yamamoto R, viktorandreevichmorozov, Choi K, Moore J, Bittner R, Hidaka S, Wei Z, nullmightybofo, Here\u00f1\u00fa D, St\u00f6ter F-R, Friesch P, Weiss A, Vollrath M, Kim T, Thassilo (2021)\u201clibrosa\/librosa: 0.8.1rc2,\u201d May [Online]. Available: https:\/\/doi.org\/10.5281\/zenodo.4792298"},{"key":"19017_CR56","unstructured":"Jiang D-N, Lu L, Zhang H-J, Tao J-H, Cai LH (2002)\u201cMusic type classification by spectral contrast feature,\u201d in Proceedings. IEEE International Conference on Multimedia and Expo, vol 1. IEEE, pp 113\u2013116"},{"key":"19017_CR57","doi-asserted-by":"crossref","unstructured":"Harte C, Sandler M, Gasser M 2006 \u201cDetecting harmonic change in musical audio,\u201d in Proceedings of the 1st ACM workshop on Audio and music computing multimedia pp 21\u201326","DOI":"10.1145\/1178723.1178727"},{"key":"19017_CR58","doi-asserted-by":"crossref","unstructured":"Rosen S (1992) \u201cTemporal information in speech: acoustic, auditory and linguistic aspects,\u201d Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences 336(1278):367\u2013373","DOI":"10.1098\/rstb.1992.0070"},{"issue":"1","key":"19017_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.9790\/4200-04110105","volume":"4","author":"D Shete","year":"2014","unstructured":"Shete D, Patil S, Patil S (2014) Zero crossing rate and energy of the speech signal of devanagari script. IOSR-JVSP 4(1):1\u20135","journal-title":"IOSR-JVSP"},{"issue":"7","key":"19017_CR60","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.3390\/s19071733","volume":"19","author":"Y Su","year":"2019","unstructured":"Su Y, Zhang K, Wang J, Madani K (2019) Environment sound classification using a two-stream cnn based on decision-level fusion. Sensors 19(7):1733","journal-title":"Sensors"},{"issue":"13","key":"19017_CR61","doi-asserted-by":"publisher","first-page":"5858","DOI":"10.1016\/j.eswa.2014.03.026","volume":"41","author":"CS Ooi","year":"2014","unstructured":"Ooi CS, Seng KP, Ang L-M, Chew LW (2014) A new approach of audio emotion recognition. Expert systems with applications 41(13):5858\u20135869","journal-title":"Expert systems with applications"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19017-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19017-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19017-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T13:17:52Z","timestamp":1731590272000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19017-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,3]]},"references-count":61,"journal-issue":{"issue":"36","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["19017"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19017-x","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,3]]},"assertion":[{"value":"18 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2024","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 declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Informed consent was not required as no human or animals were involved.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}