{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T06:02:59Z","timestamp":1769234579377,"version":"3.49.0"},"reference-count":81,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"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":[[2023,3]]},"DOI":"10.1007\/s11042-021-11839-3","type":"journal-article","created":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T19:02:25Z","timestamp":1645038145000},"page":"9693-9726","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["A feature selection model for speech emotion recognition using clustering-based population generation with hybrid of equilibrium optimizer and atom search optimization algorithm"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6890-2965","authenticated-orcid":false,"given":"Soham","family":"Chattopadhyay","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2990-7696","authenticated-orcid":false,"given":"Arijit","family":"Dey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9598-7981","authenticated-orcid":false,"given":"Pawan Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0106-7050","authenticated-orcid":false,"given":"Ali","family":"Ahmadian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8813-4086","authenticated-orcid":false,"given":"Ram","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"11839_CR1","doi-asserted-by":"crossref","unstructured":"Barros P, Weber C, Wermter S (2015) Emotional expression recognition with a cross-channel convolutional neural network for human-robot interaction. In: 2015 IEEE- RAS 15Th international conference on humanoid robots (Humanoids), IEEE, pp 582\u2013587","DOI":"10.1109\/HUMANOIDS.2015.7363421"},{"key":"11839_CR2","doi-asserted-by":"crossref","unstructured":"Blum A, Mitchell T (1998) Combining labeled and unlabeled data with co-training. In: Proceedings of the eleventh annual conference on Computational learning theory, pp 92\u2013100","DOI":"10.1145\/279943.279962"},{"key":"11839_CR3","doi-asserted-by":"crossref","unstructured":"Boigne J, Liyanage B, \u00d6strem T (2020) Recognizing more emotions with less data using self-supervised transfer learning. arXiv:201105585","DOI":"10.20944\/preprints202008.0645.v1"},{"issue":"4","key":"11839_CR4","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1023\/A:1020499411651","volume":"5","author":"A Bookstein","year":"2002","unstructured":"Bookstein A, Kulyukin VA, Raita T (2002) Generalized hamming distance. Inf Retr 5(4):353\u2013375","journal-title":"Inf Retr"},{"key":"11839_CR5","doi-asserted-by":"crossref","unstructured":"Burkhardt F, Paeschke A, Rolfes M, Sendlmeier WF, Weiss B (2005) A database of german emotional speech. In: Ninth european conference on speech communication and technology","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"4","key":"11839_CR6","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso C, Bulut M, Lee CC, Kazemzadeh A, Mower E, Kim S, Chang JN, Lee S, Narayanan SS (2008) Iemocap: Interactive emotional dyadic motion capture database. Lang Resour Eval 42(4):335\u2013359","journal-title":"Lang Resour Eval"},{"key":"11839_CR7","doi-asserted-by":"publisher","first-page":"75393","DOI":"10.1109\/ACCESS.2020.2988157","volume":"8","author":"B Chatterjee","year":"2020","unstructured":"Chatterjee B, Bhattacharyya T, Ghosh KK, Singh PK, Geem ZW, Sarkar R (2020) Late acceptance hill climbing based social ski driver algorithm for feature selection. IEEE Access 8:75393\u201375408","journal-title":"IEEE Access"},{"key":"11839_CR8","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1016\/j.ins.2019.09.005","volume":"509","author":"L Chen","year":"2020","unstructured":"Chen L, Su W, Feng Y, Wu M, She J, Hirota K (2020) Two-layer fuzzy multiple random forest for speech emotion recognition in human-robot interaction. Inf Sci 509:150\u2013163","journal-title":"Inf Sci"},{"key":"11839_CR9","unstructured":"Chibelushi CC, Bourel F (2003) Facial expression recognition: a brief tutorial overview. CVonline: On-Line Compendium of Computer Vision 9"},{"key":"11839_CR10","doi-asserted-by":"crossref","unstructured":"Cummins N, Amiriparian S, Hagerer G, Batliner A, Steidl S, Schuller BW (2017) An image-based deep spectrum feature representation for the recognition of emotional speech. In: Proceedings of the 25th ACM international conference on Multimedia, pp 478\u2013484","DOI":"10.1145\/3123266.3123371"},{"key":"11839_CR11","doi-asserted-by":"publisher","first-page":"107360","DOI":"10.1016\/j.apacoust.2020.107360","volume":"166","author":"F Daneshfar","year":"2020","unstructured":"Daneshfar F, Kabudian SJ, Neekabadi A (2020) Speech emotion recognition using hybrid spectral-prosodic features of speech signal\/glottal waveform, metaheuristic-based dimensionality reduction, and gaussian elliptical basis function network classifier. Appl Acoust 166:107360","journal-title":"Appl Acoust"},{"key":"11839_CR12","doi-asserted-by":"crossref","unstructured":"Das A, Das HS, Das HS (2020) Impact of cuckoo algorithm in speech processing. In: Applications of cuckoo search algorithm and its variants, Springer, pp 207\u2013228","DOI":"10.1007\/978-981-15-5163-5_9"},{"key":"11839_CR13","doi-asserted-by":"crossref","unstructured":"Dey A, Chattopadhyay S, Singh PK, Ahmadian A, Ferrara M, Sarkar R (2020) A hybrid meta-heuristic feature selection method using golden ratio and equilibrium optimization algorithms for speech emotion recognition, vol 8","DOI":"10.1109\/ACCESS.2020.3035531"},{"key":"11839_CR14","doi-asserted-by":"crossref","unstructured":"Emary E, Zawbaa HM, Grosan C, Hassenian AE (2015) Feature subset selection approach by gray-wolf optimization. In: Afro-European conference for industrial advancement, Springer, pp 1\u201313","DOI":"10.1007\/978-3-319-13572-4_1"},{"key":"11839_CR15","doi-asserted-by":"crossref","unstructured":"Eyben F, Weninger F, Gross F, Schuller B (2013) Recent developments in opensmile, the munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM international conference on Multimedia, pp 835\u2013838","DOI":"10.1145\/2502081.2502224"},{"key":"11839_CR16","doi-asserted-by":"publisher","first-page":"105190","DOI":"10.1016\/j.knosys.2019.105190","volume":"191","author":"A Faramarzi","year":"2020","unstructured":"Faramarzi A, Heidarinejad M, Stephens B, Mirjalili S (2020) Equilibrium optimizer: a novel optimization algorithm. Knowl-Based Syst 191:105190","journal-title":"Knowl-Based Syst"},{"key":"11839_CR17","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neunet.2017.02.013","volume":"92","author":"HM Fayek","year":"2017","unstructured":"Fayek HM, Lech M, Cavedon L (2017) Evaluating deep learning architectures for speech emotion recognition. Neural Netw 92:60\u201368","journal-title":"Neural Netw"},{"key":"11839_CR18","doi-asserted-by":"crossref","unstructured":"Geem ZW, Kim JH, Loganathan GV (2001) A new heuristic optimization algorithm:, harmony search. simulation 76(2):60\u201368","DOI":"10.1177\/003754970107600201"},{"key":"11839_CR19","doi-asserted-by":"publisher","first-page":"83548","DOI":"10.1109\/ACCESS.2020.2991543","volume":"8","author":"KK Ghosh","year":"2020","unstructured":"Ghosh KK, Ahmed S, Singh PK, Geem ZW, Sarkar R (2020a) Improved binary sailfish optimizer based on adaptive \u03b2-hill climbing for feature selection. IEEE Access 8:83548\u201383560","journal-title":"IEEE Access"},{"issue":"1","key":"11839_CR20","first-page":"1598","volume":"29","author":"M Ghosh","year":"2020","unstructured":"Ghosh M, Guha R, Alam I, Lohariwal P, Jalan D, Sarkar R (2020) Binary genetic swarm optimization: A combination of ga and pso for feature selection. J Intell Syst 29(1):1598\u20131610","journal-title":"J Intell Syst"},{"key":"11839_CR21","doi-asserted-by":"crossref","unstructured":"Gideon J, Provost EM, Mcinnis M (2016) Mood state prediction from speech of varying acoustic quality for individuals with bipolar disorder. In: 2016 IEEE International conference on acoustics, speech and signal processing (ICASSP) IEEE pp 2359-2363","DOI":"10.1109\/ICASSP.2016.7472099"},{"key":"11839_CR22","unstructured":"Goldberg DE, Samtani MP (1986) Engineering optimization via genetic algorithm. In: Electronic computation, ASCE, pp 471\u2013482"},{"key":"11839_CR23","doi-asserted-by":"publisher","first-page":"149398","DOI":"10.1109\/ACCESS.2019.2945596","volume":"7","author":"NA Golilarz","year":"2019","unstructured":"Golilarz NA, Addeh A, Gao H, Ali L, Roshandeh AM, Munir HM, Khan RU (2019) A new automatic method for control chart patterns recognition based on convnet and harris hawks meta heuristic optimization algorithm. IEEE Access 7:149398\u2013149405","journal-title":"IEEE Access"},{"issue":"1","key":"11839_CR24","first-page":"1453","volume":"29","author":"R Guha","year":"2019","unstructured":"Guha R, Ghosh M, Singh PK, Sarkar R, Nasipuri M (2019) M-hmoga: a new multi-objective feature selection algorithm for handwritten numeral classification. J Intell Syst 29(1):1453\u20131467","journal-title":"J Intell Syst"},{"key":"11839_CR25","doi-asserted-by":"publisher","first-page":"106341","DOI":"10.1016\/j.asoc.2020.106341","volume":"93","author":"R Guha","year":"2020","unstructured":"Guha R, Ghosh M, Chakrabarti A, Sarkar R, Mirjalili S (2020) Introducing clustering based population in binary gravitational search algorithm for feature selection. Appl Soft Comput 93:106341","journal-title":"Appl Soft Comput"},{"key":"11839_CR26","doi-asserted-by":"publisher","first-page":"182868","DOI":"10.1109\/ACCESS.2020.3028121","volume":"8","author":"S Guha","year":"2020","unstructured":"Guha S, Das A, Singh PK, Ahmadian A, Senu N, Sarkar R (2020) Hybrid feature selection method based on harmony search and naked mole-rat algorithms for spoken language identification from audio signals. IEEE Access 8:182868\u2013182887","journal-title":"IEEE Access"},{"key":"11839_CR27","doi-asserted-by":"crossref","unstructured":"Gupta H (2016) Lpc and lpcc method of feature extraction in speech recognition system. In: 2016 6Th international conference-cloud system and big data engineering (Confluence) IEEE, pp 498-502","DOI":"10.1109\/CONFLUENCE.2016.7508171"},{"issue":"5","key":"11839_CR28","doi-asserted-by":"publisher","first-page":"479","DOI":"10.3390\/e21050479","volume":"21","author":"N Hajarolasvadi","year":"2019","unstructured":"Hajarolasvadi N, Demirel H (2019) 3d cnn-based speech emotion recognition using k-means clustering and spectrograms. Entropy 21(5):479","journal-title":"Entropy"},{"key":"11839_CR29","doi-asserted-by":"publisher","first-page":"92871","DOI":"10.1109\/ACCESS.2019.2928017","volume":"7","author":"J Huang","year":"2019","unstructured":"Huang J, Chen B, Yao B, He W (2019) Ecg arrhythmia classification using stft-based spectrogram and convolutional neural network. IEEE Access 7:92871\u201392880","journal-title":"IEEE Access"},{"issue":"5","key":"11839_CR30","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1007\/s12652-017-0644-8","volume":"10","author":"Y Huang","year":"2019","unstructured":"Huang Y, Tian K, Wu A, Zhang G (2019) Feature fusion methods research based on deep belief networks for speech emotion recognition under noise condition. J Ambient Intell Humaniz Comput 10(5):1787\u20131798","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"11839_CR31","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":"11839_CR32","unstructured":"Jackson P, Haq S (2014) Surrey audio-visual expressed emotion (savee) database. University of Surrey: Guildford, UK"},{"issue":"1","key":"11839_CR33","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.bbe.2019.05.005","volume":"40","author":"B Karan","year":"2020","unstructured":"Karan B, Sahu SS, Mahto K (2020) Parkinson disease prediction using intrinsic mode function based features from speech signal. Biocybern Biomed Eng 40(1):249\u2013264","journal-title":"Biocybern Biomed Eng"},{"key":"11839_CR34","doi-asserted-by":"publisher","first-page":"119516","DOI":"10.1109\/ACCESS.2020.3005664","volume":"8","author":"Lai H","year":"2020","unstructured":"Lai H, Chen H, Wu S (2020) Different contextual window sizes based rnns for multimodal emotion detection in interactive conversations. IEEE Access 8:119516\u2013119526","journal-title":"IEEE Access"},{"key":"11839_CR35","doi-asserted-by":"crossref","unstructured":"Latif S, Rana R, Khalifa S, Jurdak R, Epps J (2019) Direct modelling of speech emotion from raw speech. arXiv:190403833","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"11839_CR36","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.neucom.2018.05.005","volume":"309","author":"ZT Liu","year":"2018","unstructured":"Liu ZT, Xie Q, Wu M, Cao WH, Mei Y, Mao JW (2018) Speech emotion recognition based on an improved brain emotion learning model. Neurocomputing 309:145\u2013156","journal-title":"Neurocomputing"},{"issue":"5","key":"11839_CR37","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":"11839_CR38","doi-asserted-by":"crossref","unstructured":"Lu Z, Cao L, Zhang Y, Chiu CC, Fan J (2020) Speech sentiment analysis via pre-trained features from end-to-end asr models. In: ICASSP 2020-2020 IEEE International conference on acoustics, speech and signal processing (ICASSP), IEEE pp 7149-7153","DOI":"10.1109\/ICASSP40776.2020.9052937"},{"key":"11839_CR39","doi-asserted-by":"crossref","unstructured":"Mahdhaoui A, Chetouani M (2010) Emotional speech classification based on multi view characterization. In: 2010 20th international conference on pattern recognition, IEEE, pp 4488\u20134491","DOI":"10.1109\/ICPR.2010.1090"},{"key":"11839_CR40","doi-asserted-by":"crossref","unstructured":"Mao S, Ching P, Lee T (2020) Eigenemo: Spectral utterance representation using dynamic mode decomposition for speech emotion classification.arXiv:200806665","DOI":"10.21437\/Interspeech.2020-1762"},{"key":"11839_CR41","doi-asserted-by":"crossref","unstructured":"Mao S, Ching P, Lee T (2020) Emotion profile refinery for speech emotion classification. arXiv:200805259","DOI":"10.21437\/Interspeech.2020-1771"},{"issue":"1","key":"11839_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13042-019-00928-3","volume":"11","author":"H Mukherjee","year":"2020","unstructured":"Mukherjee H, Obaidullah SM, Santosh K, Phadikar S, Roy K (2020) A lazy learning-based language identification from speech using mfcc-2 features. Int J Mach Learn Cybern 11(1):1\u201314","journal-title":"Int J Mach Learn Cybern"},{"issue":"3","key":"11839_CR43","doi-asserted-by":"publisher","first-page":"e0120344","DOI":"10.1371\/journal.pone.0120344","volume":"10","author":"H Muthusamy","year":"2015","unstructured":"Muthusamy H, Polat K, Yaacob S (2015) Particle swarm optimization based feature enhancement and feature selection for improved emotion recognition in speech and glottal signals. PloS one 10(3):e0120344","journal-title":"PloS one"},{"key":"11839_CR44","doi-asserted-by":"publisher","first-page":"102763","DOI":"10.1016\/j.dsp.2020.102763","volume":"104","author":"S Nagarajan","year":"2020","unstructured":"Nagarajan S, Nettimi SSS, Kumar LS, Nath MK, Kanhe A (2020) Speech emotion recognition using cepstral features extracted with novel triangular filter banks based on bark and erb frequency scales. Digit Signal Process 104:102763","journal-title":"Digit Signal Process"},{"key":"11839_CR45","doi-asserted-by":"crossref","unstructured":"Nantasri P, Phaisangittisagul E, Karnjana J, Boonkla S, Keerativittayanun S, Rugchatjaroen A, Usanavasin S, Shinozaki T (2020) A light-weight artificial neural network for speech emotion recognition using average values of mfccs and their derivatives. In: 2020 17Th international conference on electrical engineering\/electronics, computer, telecommunications and information technology (ECTI-CON) IEEE, pp 41-44","DOI":"10.1109\/ECTI-CON49241.2020.9158221"},{"key":"11839_CR46","doi-asserted-by":"crossref","unstructured":"Navyasri M, RajeswarRao R, DaveeduRaju A, Ramakrishnamurthy M (2017) Robust features for emotion recognition from speech by using gaussian mixture model classification. In: International conference on information and communication technology for intelligent systems, Springer, pp 437\u2013444","DOI":"10.1007\/978-3-319-63645-0_50"},{"issue":"2","key":"11839_CR47","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1007\/s00500-019-03949-w","volume":"24","author":"AF Nematollahi","year":"2020","unstructured":"Nematollahi AF, Rahiminejad A, Vahidi B (2020) A novel meta-heuristic optimization method based on golden ratio in nature. Soft Comput 24 (2):1117\u20131151","journal-title":"Soft Comput"},{"key":"11839_CR48","doi-asserted-by":"crossref","unstructured":"Nguyen D, Nguyen K, Sridharan S, Abbasnejad I, Dean D, Fookes C (2018) Meta transfer learning for facial emotion recognition","DOI":"10.1109\/ICPR.2018.8545411"},{"issue":"4","key":"11839_CR49","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1016\/S0167-6393(03)00099-2","volume":"41","author":"TL Nwe","year":"2003","unstructured":"Nwe TL, Foo SW, De Silva LC (2003) Speech emotion recognition using hidden markov models. Speech Commun 41(4):603\u2013623","journal-title":"Speech Commun"},{"key":"11839_CR50","unstructured":"Ortega MGS, Rodr\u00edguez LF, Gutierrez-Garcia JO (2019) Towards emotion recognition from contextual information using machine learning. Journal of Ambient Intelligence and Humanized Computing pp 1\u201321"},{"issue":"6","key":"11839_CR51","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1057\/palgrave.jors.2600781","volume":"48","author":"IH Osman","year":"1997","unstructured":"Osman IH, Kelly JP (1997) Meta-heuristics theory and applications. J Oper Res Soc 48(6):657\u2013657","journal-title":"J Oper Res Soc"},{"key":"11839_CR52","doi-asserted-by":"crossref","unstructured":"Pao TL, Chen YT, Yeh JH, Liao WY (2005) Combining acoustic features for improved emotion recognition in mandarin speech. In: International conference on affective computing and intelligent interaction, Springer, pp 279\u2013285","DOI":"10.1007\/11573548_36"},{"key":"11839_CR53","doi-asserted-by":"crossref","unstructured":"Patil A, Samant S, Ramtekkar M, Ragaji S, Khanapuri J (2020) Intelligent voice assistant. Available at SSRN 3568721","DOI":"10.2139\/ssrn.3568721"},{"key":"11839_CR54","unstructured":"Peng H, Zhang Z, Wang J, Shi P (2013) Audio watermarking framework using multi-objective particle swarm optimization. PhD thesis, ICIC International"},{"key":"11839_CR55","doi-asserted-by":"crossref","unstructured":"Pepino L, Riera P, Ferrer L, Gravano A (2020) Fusion approaches for emotion recognition from speech using acoustic and text-based features. In: ICASSP 2020-2020 IEEE International conference on acoustics, speech and signal processing (ICASSP) IEEE, pp 6484-6488","DOI":"10.1109\/ICASSP40776.2020.9054709"},{"issue":"5","key":"11839_CR56","doi-asserted-by":"publisher","first-page":"1126","DOI":"10.35940\/ijeat.E1027.069520","volume":"9","author":"H Qazi","year":"2020","unstructured":"Qazi H, Kaushik BN (2020) A hybrid technique using CNN+LSTM for speech emotion recognition. International Journal of Engineering and Advanced Technology (IJEAT) 9(5):1126\u20131130. https:\/\/doi.org\/10.35940\/ijeat.E1027.069520","journal-title":"International Journal of Engineering and Advanced Technology (IJEAT)"},{"key":"11839_CR57","doi-asserted-by":"crossref","unstructured":"Rajak R, Mall R (2019) Emotion recognition from audio, dimensional and discrete categorization using cnns. In: TENCON 2019-2019 IEEE Region 10 Conference (TENCON), IEEE, pp 301-305","DOI":"10.1109\/TENCON.2019.8929459"},{"key":"11839_CR58","unstructured":"Rajasekhar B, Kamaraju M, Sumalatha V (2020) A novel speech emotion recognition model using mean update of particle swarm and whale optimization-based deep belief network. Data Technologies and Applications"},{"issue":"4","key":"11839_CR59","doi-asserted-by":"publisher","first-page":"e13033","DOI":"10.1111\/ecc.13033","volume":"28","author":"R Rana","year":"2019","unstructured":"Rana R, Latif S, Gururajan R, Gray A, Mackenzie G, Humphris G, Dunn J (2019) Automated screening for distress: a perspective for the future. Eur J Cancer Care 28(4):e13033","journal-title":"Eur J Cancer Care"},{"key":"11839_CR60","unstructured":"Ren Z, Kong Q, Qian K, Plumbley MD, Schuller B et al (2018) Attention-based Convolutional neural networks for acoustic scene classification. In: DCASE 2018 Workshop Proceedings"},{"issue":"8","key":"11839_CR61","doi-asserted-by":"publisher","first-page":"2816","DOI":"10.3390\/app10082816","volume":"10","author":"S Saha","year":"2020","unstructured":"Saha S, Ghosh M, Ghosh S, Sen S, Singh PK, Geem ZW, Sarkar R (2020) Feature selection for facial emotion recognition using cosine similarity-based harmony search algorithm. Appl Sci 10(8):2816","journal-title":"Appl Sci"},{"key":"11839_CR62","doi-asserted-by":"crossref","unstructured":"Saldanha JC, Suvarna M (2020) Perceptual linear prediction feature as an indicator of dysphonia. In: Advances in control instrumentation systems, Springer, pp 51\u201364","DOI":"10.1007\/978-981-15-4676-1_5"},{"key":"11839_CR63","doi-asserted-by":"crossref","unstructured":"Schuller B, Rigoll G, Lang M (2003) Hidden markov model-based speech emotion recognition. In: 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP\u201903)., IEEE, vol 2, pp II\u20131","DOI":"10.1109\/ICME.2003.1220939"},{"key":"11839_CR64","doi-asserted-by":"publisher","first-page":"158125","DOI":"10.1109\/ACCESS.2020.3019809","volume":"8","author":"Sheikh KH","year":"2020","unstructured":"Sheikh KH, Ahmed S, Mukhopadhyay K, Singh PK, Yoon JH, Geem ZW, Sarkar R (2020) Ehhm: Electrical harmony based hybrid meta-heuristic for feature selection. IEEE Access 8:158125\u2013158141","journal-title":"IEEE Access"},{"key":"11839_CR65","doi-asserted-by":"crossref","unstructured":"Shetty S, Hegde S (2020) Automatic classification of carnatic music instruments using mfcc and lpc. In: Data management, analytics and innovation, Springer, pp 463-474","DOI":"10.1007\/978-981-32-9949-8_32"},{"key":"11839_CR66","doi-asserted-by":"crossref","unstructured":"da Silva R, Valter Filho M, Souza M (2020) Interaffection of multiple datasets with neural networks in speech emotion recognition. In: Anais do XVII encontro nacional de intelig\u00eancia artificial e computacional, SBC pp 342-353","DOI":"10.5753\/eniac.2020.12141"},{"key":"11839_CR67","unstructured":"Singh A (2020) Speech emotion recognition using enhanced cat swarm optimization algorithm. International Journal of Information Technology (IJIT) 6(5)"},{"key":"11839_CR68","doi-asserted-by":"crossref","unstructured":"Su BH, Chang CM, Lin YS, Lee CC (2020) Improving speech emotion recognition using graph attentive bi-directional gated recurrent unit network. Proc Interspeech 2020 pp 506\u2013510","DOI":"10.21437\/Interspeech.2020-1733"},{"issue":"6","key":"11839_CR69","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/S0020-0190(02)00447-7","volume":"85","author":"IC Trelea","year":"2003","unstructured":"Trelea IC (2003) The particle swarm optimization algorithm: convergence analysis and parameter selection. Inf Process Lett 85(6):317\u2013325","journal-title":"Inf Process Lett"},{"issue":"1","key":"11839_CR70","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":"11839_CR71","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/j.neucom.2020.02.085","volume":"398","author":"K Wang","year":"2020","unstructured":"Wang K, Su G, Liu L, Wang S (2020) Wavelet packet analysis for speaker-independent emotion recognition. Neurocomputing 398:257\u2013264","journal-title":"Neurocomputing"},{"issue":"1","key":"11839_CR72","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","volume":"1","author":"DH Wolpert","year":"1997","unstructured":"Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1(1):67\u201382","journal-title":"IEEE Trans Evol Comput"},{"issue":"1","key":"11839_CR73","first-page":"10","volume":"2","author":"CH Wu","year":"2010","unstructured":"Wu CH, Liang WB (2010) Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels. IEEE Trans Affect Comput 2(1):10\u201321","journal-title":"IEEE Trans Affect Comput"},{"key":"11839_CR74","doi-asserted-by":"crossref","unstructured":"Wu W, Zhang C, Woodland PC (2020) Emotion recognition by fusing time synchronous and time asynchronous representations. arXiv:201014102","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"11839_CR75","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.eswa.2016.10.035","volume":"69","author":"C Yogesh","year":"2017","unstructured":"Yogesh C, Hariharan M, Ngadiran R, Adom AH, Yaacob S, Berkai C, Polat K (2017) A new hybrid pso assisted biogeography-based optimization for emotion and stress recognition from speech signal. Expert Syst Appl 69:149\u2013158","journal-title":"Expert Syst Appl"},{"issue":"5","key":"11839_CR76","doi-asserted-by":"publisher","first-page":"713","DOI":"10.3390\/electronics9050713","volume":"9","author":"Y Yu","year":"2020","unstructured":"Yu Y, Kim YJ (2020) Attention-lstm-attention model for speech emotion recognition and analysis of iemocap database. Electronics 9(5):713","journal-title":"Electronics"},{"key":"11839_CR77","doi-asserted-by":"crossref","unstructured":"Zamil AAA, Hasan S, Baki SMJ, Adam JM, Zaman I (2019) Emotion detection from speech signals using voting mechanism on classified frames. In: 2019 International conference on robotics, electrical and signal processing techniques (ICREST), IEEE, pp 281\u2013285","DOI":"10.1109\/ICREST.2019.8644168"},{"key":"11839_CR78","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"},{"key":"11839_CR79","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.knosys.2018.08.030","volume":"163","author":"W Zhao","year":"2019","unstructured":"Zhao W, Wang L, Zhang Z (2019) Atom search optimization and its application to solve a hydrogeologic parameter estimation problem. Knowl Based Syst 163:283\u2013304","journal-title":"Knowl Based Syst"},{"key":"11839_CR80","doi-asserted-by":"publisher","first-page":"103300","DOI":"10.1016\/j.engappai.2019.103300","volume":"87","author":"W Zhao","year":"2020","unstructured":"Zhao W, Zhang Z, Wang L (2020) Manta ray foraging optimization: an effective bio-inspired optimizer for engineering applications. Eng Appl Artif Intell 87:103300","journal-title":"Eng Appl Artif Intell"},{"issue":"4","key":"11839_CR81","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1109\/TAFFC.2017.2650899","volume":"9","author":"Y Zhu","year":"2017","unstructured":"Zhu Y, Shang Y, Shao Z, Guo G (2017) Automated depression diagnosis based on deep networks to encode facial appearance and dynamics. IEEE Trans Affect Comput 9(4):578\u2013584","journal-title":"IEEE Trans Affect Comput"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11839-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11839-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11839-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T16:19:16Z","timestamp":1677773956000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11839-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,16]]},"references-count":81,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["11839"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11839-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,16]]},"assertion":[{"value":"31 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 February 2022","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 author declare that there have no conflict of interest regarding the publication of the paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}]}}