{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T23:17:31Z","timestamp":1781479051481,"version":"3.54.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s10772-024-10095-8","type":"journal-article","created":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T16:02:01Z","timestamp":1711814521000},"page":"239-254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["A computationally efficient speech emotion recognition system employing machine learning classifiers and ensemble learning"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4054-6801","authenticated-orcid":false,"given":"N.","family":"Aishwarya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanwaljeet","family":"Kaur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karthik","family":"Seemakurthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,30]]},"reference":[{"key":"10095_CR1","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.specom.2020.04.005","volume":"122","author":"L Abdel-Hamid","year":"2020","unstructured":"Abdel-Hamid, L. (2020). Egyptian Arabic speech emotion recognition using prosodic, spectral and wavelet features. Speech Communication, 122, 19\u201330. https:\/\/doi.org\/10.1016\/j.specom.2020.04.005","journal-title":"Speech Communication"},{"key":"10095_CR2","doi-asserted-by":"publisher","first-page":"122136","DOI":"10.1109\/ACCESS.2022.3223444","volume":"10","author":"ZK Abdul","year":"2022","unstructured":"Abdul, Z. K., & Al-Talabani, A. K. (2022). Mel frequency cepstral coefficient and its applications: A review. IEEE Access, 10, 122136\u2013122158. https:\/\/doi.org\/10.1109\/ACCESS.2022.3223444","journal-title":"IEEE Access"},{"key":"10095_CR3","doi-asserted-by":"publisher","unstructured":"Afreen, N., Patel, R., Ahmed, M., & Sameer, M. (2021). A novel machine learning approach using boosting algorithm for liver disease classification. In 2021 5th international conference on information systems and computer networks (ISCON) (pp. 1\u20135). https:\/\/doi.org\/10.1109\/ISCON52037.2021.9702488","DOI":"10.1109\/ISCON52037.2021.9702488"},{"key":"10095_CR4","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1016\/j.procs.2023.03.083","volume":"220","author":"N Aishwarya","year":"2023","unstructured":"Aishwarya, N., Prabhakaran, K. M., Debebe, F. T., Reddy, M. S. S. A., & Pranavee, P. (2023). Skin cancer diagnosis with Yolo deep neural network. Procedia Computer Science, 220, 651\u2013658. https:\/\/doi.org\/10.1016\/j.procs.2023.03.083","journal-title":"Procedia Computer Science"},{"key":"10095_CR5","doi-asserted-by":"publisher","first-page":"18799","DOI":"10.1007\/s11042-022-14272-2","volume":"82","author":"N Aishwarya","year":"2023","unstructured":"Aishwarya, N., Praveena, N. G., & Priyanka, S. (2023). Smart farming for detection and identification of tomato plant diseases using light weight deep neural network. Multimedia Tools and Applications, 82, 18799\u201318810. https:\/\/doi.org\/10.1007\/s11042-022-14272-2","journal-title":"Multimedia Tools and Applications"},{"issue":"6","key":"10095_CR6","first-page":"39","volume":"5","author":"K Akash","year":"2016","unstructured":"Akash, K., Aschana, M., Abhijith, M., & Shuvalila, M. (2016). Speech based emotion recognition system. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 5(6), 39\u201342.","journal-title":"International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering"},{"key":"10095_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","volume":"116","author":"MB Akcay","year":"2020","unstructured":"Akcay, M. B., & Oguz, K. (2020). Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Communication, 116, 56\u201376.","journal-title":"Speech Communication"},{"key":"10095_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108046","volume":"179","author":"J Ancilin","year":"2021","unstructured":"Ancilin, J., & Milton, A. (2021). Improved speech emotion recognition with Mel frequency magnitude coefficient. Applied Acoustics, 179, 108046. https:\/\/doi.org\/10.1016\/j.apacoust.2021.108046","journal-title":"Applied Acoustics"},{"key":"10095_CR9","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.csl.2013.07.002","volume":"28","author":"JP Arias","year":"2014","unstructured":"Arias, J. P., Busso, C., & Yoma, N. B. (2014). Shape-based modeling of the fundamental frequency contour for emotion detection in speech. Computer Speech and Language, 28, 278\u2013294.","journal-title":"Computer Speech and Language"},{"key":"10095_CR10","doi-asserted-by":"publisher","unstructured":"Badshah, A. M., Ahmad, J., Rahim, N., & Baik S. W. (2017). Speech emotion recognition from spectrograms with deep convolutional neural network. In 2017 international conference on platform technology and service (PlatCon) (pp. 1\u20135). Busan. https:\/\/doi.org\/10.1109\/PlatCon.2017.7883728","DOI":"10.1109\/PlatCon.2017.7883728"},{"key":"10095_CR11","doi-asserted-by":"publisher","unstructured":"Cheng, H., & Guo, Y. (2022). Data shift: A cross-modal data augmentation method for speech recognition and machine translation. In 2022 4th international conference on natural language processing (ICNLP) (pp. 341\u2013344). https:\/\/doi.org\/10.1109\/ICNLP55136.2022.00062","DOI":"10.1109\/ICNLP55136.2022.00062"},{"key":"10095_CR12","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1016\/j.procs.2022.12.187","volume":"216","author":"A Chowanda","year":"2023","unstructured":"Chowanda, A., Iswanto, I. A., & Andangsari, E. W. (2023). Exploring deep learning algorithm to model emotions recognition from speech. Procedia Computer Science, 216, 706\u2013713. https:\/\/doi.org\/10.1016\/j.procs.2022.12.187","journal-title":"Procedia Computer Science"},{"key":"10095_CR13","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s10772-020-09713-y","volume":"23","author":"A Christy","year":"2020","unstructured":"Christy, A., Vaithyasubramanian, S., & Jesudoss, A. (2020). Multimodal speech emotion recognition and classification using convolutional neural network techniques. International Journal of Speech Technology, 23, 381\u2013388. https:\/\/doi.org\/10.1007\/s10772-020-09713-y","journal-title":"International Journal of Speech Technology"},{"key":"10095_CR14","doi-asserted-by":"publisher","unstructured":"Dolka, H., Vm, A. X., & Juliet, S. (2021). Speech emotion recognition using ANN on MFCC features. In 2021 3rd international conference on signal processing and communication (ICPSC) (pp. 431\u2013435). https:\/\/doi.org\/10.1109\/ICSPC51351.2021.9451810","DOI":"10.1109\/ICSPC51351.2021.9451810"},{"issue":"3","key":"10095_CR15","first-page":"182","volume":"39","author":"K Duouis","year":"2011","unstructured":"Duouis, K., & Pichora-Fuller, M. K. (2011). Recognition of emotional speech for younger and older talkers: Behavioural findings from the toronto emotional speech set. Canadian Acoustics - Acoustique Canadienne, 39(3), 182\u2013183.","journal-title":"Canadian Acoustics - Acoustique Canadienne"},{"key":"10095_CR16","doi-asserted-by":"publisher","unstructured":"Fatourechi, M., Ward, R. K., Mason, S. G., Huggins, J., Schl\u00f6gl, A., & Birch, G. E. (2008). Comparison of evaluation metrics in classification applications with imbalanced datasets. In 2008 seventh international conference on machine learning and applications (pp. 777\u2013782).https:\/\/doi.org\/10.1109\/ICMLA.2008.34","DOI":"10.1109\/ICMLA.2008.34"},{"key":"10095_CR17","doi-asserted-by":"publisher","unstructured":"Ghosh S, Dasgupta A and Swetapadma A. (2019). A study on support vector machine based linear and non-linear pattern classification. In 2019 international conference on intelligent sustainable systems (ICISS) (pp. 24\u201328). https:\/\/doi.org\/10.1109\/ISS1.2019.8908018","DOI":"10.1109\/ISS1.2019.8908018"},{"key":"10095_CR18","doi-asserted-by":"publisher","unstructured":"Gupta, K., & Gupta, D. (2022). An analysis on LPC, RASTA and MFCC techniques in Automatic Speech recognition system. In 2016 6th international conference - cloud system and big data engineering (confluence) (pp. 493\u2013497). https:\/\/doi.org\/10.1109\/CONFLUENCE.2016.7508170","DOI":"10.1109\/CONFLUENCE.2016.7508170"},{"key":"10095_CR19","doi-asserted-by":"crossref","unstructured":"Haq, S., & Jackson, P. J. B. (2010). Multimodal emotion recognition. In W. Wang (Ed.), Machine audition: Principles, algorithms and systems (pp. 398\u2013423). IGI global.","DOI":"10.4018\/978-1-61520-919-4.ch017"},{"key":"10095_CR20","doi-asserted-by":"publisher","unstructured":"Ho, T. K. (1995). Random decision forests. In Proceedings of 3rd international conference on document analysis and recognition (Vol. 1, pp. 278\u2013282). https:\/\/doi.org\/10.1109\/ICDAR.1995.598994","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"10095_CR21","doi-asserted-by":"publisher","unstructured":"Huang, Y., & Li, L. (2011). Naive Bayes classification algorithm based on small sample set. In 2011 IEEE international conference on cloud computing and intelligence systems (pp. 34\u201339). https:\/\/doi.org\/10.1109\/CCIS.2011.6045027","DOI":"10.1109\/CCIS.2011.6045027"},{"key":"10095_CR22","doi-asserted-by":"publisher","unstructured":"Jaiswal, J. K., & Samikannu, R. (2021). Application of random forest algorithm on feature subset selection and classification and regression. In 2017 world congress on computing and communication technologies (WCCCT) (pp. 65\u201368). https:\/\/doi.org\/10.1109\/WCCCT.2016.25","DOI":"10.1109\/WCCCT.2016.25"},{"key":"10095_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2022.112512","volume":"162","author":"S Jothimani","year":"2022","unstructured":"Jothimani, S., & Premalatha, K. (2022). MFF-SAug: Multi feature fusion with spectrogram augmentation of speech emotion recognition using convolution neural network. Chaos, Solitons & Fractals, 162, 112512. https:\/\/doi.org\/10.1016\/j.chaos.2022.112512","journal-title":"Chaos, Solitons & Fractals"},{"key":"10095_CR24","doi-asserted-by":"publisher","unstructured":"Kaushik, S., & Birok, R. (2021). Heart failure prediction using voting ensemble classifier. In 2021 asian conference on innovation in technology (ASIANCON) (pp. 1\u20135). https:\/\/doi.org\/10.1109\/ASIANCON51346.2021.9544871","DOI":"10.1109\/ASIANCON51346.2021.9544871"},{"key":"10095_CR25","doi-asserted-by":"publisher","unstructured":"Kumar, C. S. A., Maharana, A. D., Krishnan S. M., Hanuma, S. S. S., Lal, G. J., & Ravi V. (2023). Speech emotion recognition using CNN-LSTM and vision transformer. In Innovations in bio-inspired computing and applications (IBICA), Lecture notes in networks and systems (Vol. 649). Springer. https:\/\/doi.org\/10.1007\/978-3-031-27499-2_8","DOI":"10.1007\/978-3-031-27499-2_8"},{"key":"10095_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-9019-1_24","author":"R Kumar","year":"2021","unstructured":"Kumar, R., & Dhanya, N. (2021). Efficient speech to emotion recognition using convolutional neural network. Advances in Electrical and Computer Technologies. https:\/\/doi.org\/10.1007\/978-981-15-9019-1_24","journal-title":"Advances in Electrical and Computer Technologies"},{"issue":"5","key":"10095_CR27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","unstructured":"Livingstone, S. R., & Russo, F. A. (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":"10095_CR28","doi-asserted-by":"publisher","first-page":"22071","DOI":"10.1109\/access.2019.2898353","volume":"7","author":"R Lotfian","year":"2021","unstructured":"Lotfian, R., & Busso, C. (2021). Lexical dependent emotion detection using synthetic speech reference. IEEE Access, 7, 22071\u201322085. https:\/\/doi.org\/10.1109\/access.2019.2898353","journal-title":"IEEE Access"},{"key":"10095_CR29","doi-asserted-by":"publisher","unstructured":"Mai, X., Liao, Z., & Couillet, R. (2019). A large-scale analysis of logistic regression: Asymptotic performance and new insights. In ICASSP 2019\u20142019 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 3357\u20133361). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683376","DOI":"10.1109\/ICASSP.2019.8683376"},{"key":"10095_CR30","doi-asserted-by":"publisher","unstructured":"Matin, R., & Valles, D. (2020). A speech emotion recognition solution-based on support vector machine for children with autism spectrum disorder to help identify human emotions. In 2020 intermountain engineering, technology and computing (IETC) (pp. 1\u20136). https:\/\/doi.org\/10.1109\/IETC47856.2020.9249147","DOI":"10.1109\/IETC47856.2020.9249147"},{"issue":"2","key":"10095_CR31","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1016\/j.jksuci.2023.01.014","volume":"35","author":"A Mohammed","year":"2023","unstructured":"Mohammed, A., & Kora, R. (2023). A comprehensive review on ensemble deep learning: Opportunities and challenges. Journal of King Saud University - Computer and Information Sciences, 35(2), 757\u2013774. https:\/\/doi.org\/10.1016\/j.jksuci.2023.01.014","journal-title":"Journal of King Saud University - Computer and Information Sciences"},{"key":"10095_CR32","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1016\/j.procs.2023.01.163","volume":"218","author":"M Mohan","year":"2023","unstructured":"Mohan, M., Dhanalakshmi, P., & Kumar, R. S. (2023). Speech emotion classification using ensemble models with MFCC. Procedia Computer Science, 218, 1857\u20131868. https:\/\/doi.org\/10.1016\/j.procs.2023.01.163","journal-title":"Procedia Computer Science"},{"key":"10095_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101287","volume":"72","author":"A Mohanta","year":"2022","unstructured":"Mohanta, A., & Mittal, V. K. (2022). Analysis and classification of speech sounds of children with autism spectrum disorder using acoustic features. Computer Speech & Language, 72, 101287. https:\/\/doi.org\/10.1016\/j.csl.2021.101287","journal-title":"Computer Speech & Language"},{"key":"10095_CR34","doi-asserted-by":"publisher","unstructured":"Patel, R., & Chaware, A. (2020). Transfer learning with fine-tuned MobileNetV2 for diabetic retinopathy. In 2020 international conference for emerging technology (INCET) (pp. 1\u20134). https:\/\/doi.org\/10.1109\/INCET49848.2020.9154014","DOI":"10.1109\/INCET49848.2020.9154014"},{"key":"10095_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119633","volume":"218","author":"M Rayhan Ahmed","year":"2023","unstructured":"Rayhan Ahmed, M., Islam, S., Muzahidul Islam, A., & Shatabda, S. (2023). An ensemble 1D-CNN-LSTM-GRU model with data augmentation for speech emotion recognition. Expert Systems with Applications, 218, 119633. https:\/\/doi.org\/10.1016\/j.eswa.2023.119633","journal-title":"Expert Systems with Applications"},{"key":"10095_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-021-09854-8","author":"S Shivaprasad","year":"2021","unstructured":"Shivaprasad, S., & Sadanandam, M. (2021). Dialect recognition from Telugu speech utterances using spectral and prosodic features. International Journal of Speech Technology. https:\/\/doi.org\/10.1007\/s10772-021-09854-8","journal-title":"International Journal of Speech Technology"},{"key":"10095_CR37","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.1016\/j.procs.2023.01.227","volume":"218","author":"V Singh","year":"2023","unstructured":"Singh, V., & Prasad, S. (2023). Speech emotion recognition system using gender dependent convolution neural network. Procedia Computer Science, 218, 2533\u20132540. https:\/\/doi.org\/10.1016\/j.procs.2023.01.227","journal-title":"Procedia Computer Science"},{"key":"10095_CR38","doi-asserted-by":"publisher","unstructured":"Taunk, K., De, S., Verma, S., & Swetapadma. A. (2019). A brief review of nearest neighbor algorithm for learning and classification. In 2019 international conference on intelligent computing and control systems (ICCS) (pp. 1255\u20131260). https:\/\/doi.org\/10.1109\/ICCS45141.2019.9065747","DOI":"10.1109\/ICCS45141.2019.9065747"},{"key":"10095_CR39","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/j.procs.2022.11.076","volume":"213","author":"A Tsaregorodtsev","year":"2022","unstructured":"Tsaregorodtsev, A., Samoylov, V., Zenov, A., Zelenina, A., Petrosov, D., Pleshakova, E., Osipov, A., Ivanova, M., Petrosova, N., Lopatnuk, L., Radygin, V., & Roga, S. (2022). The architecture of the emotion recognition program by speech segments. Procedia Computer Science, 213, 338\u2013345. https:\/\/doi.org\/10.1016\/j.procs.2022.11.076","journal-title":"Procedia Computer Science"},{"key":"10095_CR40","doi-asserted-by":"publisher","unstructured":"Wang, Q. (2022). Support vector machine algorithm in machine learning. In 2022 IEEE international conference on artificial intelligence and computer applications (ICAICA) (pp. 750\u2013756). https:\/\/doi.org\/10.1109\/ICAICA54878.2022.9844516","DOI":"10.1109\/ICAICA54878.2022.9844516"},{"key":"10095_CR41","doi-asserted-by":"publisher","unstructured":"Yang, F. -J. (2018). An implementation of Naive Bayes classifier. In 2018 international conference on computational science and computational intelligence (CSCI) (pp. 301\u2013306). https:\/\/doi.org\/10.1109\/CSCI46756.2018.00065","DOI":"10.1109\/CSCI46756.2018.00065"},{"issue":"5","key":"10095_CR42","doi-asserted-by":"publisher","first-page":"1774","DOI":"10.1109\/TNNLS.2017.2673241","volume":"29","author":"S Zhang","year":"2018","unstructured":"Zhang, S., Li, X., Zong, M., Zhu, X., & Wang, R. (2018). Efficient KNN classification with different numbers of nearest neighbors. IEEE Transactions on Neural Networks and Learning Systems, 29(5), 1774\u20131785. https:\/\/doi.org\/10.1109\/TNNLS.2017.2673241","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10095-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10095-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10095-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T15:15:20Z","timestamp":1715613320000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10095-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["10095"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10095-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]},"assertion":[{"value":"30 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 March 2024","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 they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}