{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T14:45:25Z","timestamp":1787064325834,"version":"build-2736575974"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T00:00:00Z","timestamp":1657238400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T00:00:00Z","timestamp":1657238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s10772-022-09985-6","type":"journal-article","created":{"date-parts":[[2022,7,8]],"date-time":"2022-07-08T01:02:21Z","timestamp":1657242141000},"page":"707-725","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Machine learning techniques for speech emotion recognition using paralinguistic acoustic features"],"prefix":"10.1007","volume":"25","author":[{"given":"Tulika","family":"Jha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramisetty","family":"Kavya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6744-9329","authenticated-orcid":false,"given":"Jabez","family":"Christopher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vasan","family":"Arunachalam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,7,8]]},"reference":[{"key":"9985_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, E., & Christopher, J. (2020). Emotion recognition from periocular features. In International conference on machine learning, image processing, network security and data sciences (pp. 194\u2013208). Springer.","DOI":"10.1007\/978-981-15-6315-7_16"},{"key":"9985_CR2","first-page":"1038","volume":"2","author":"E Agrawal","year":"2021","unstructured":"Agrawal, E., Christopher, J. J., & Arunachalam, V. (2021). Emotion recognition through voting on expressions in multiple facial regions.\u00a0ICAART, 2, 1038\u20131045.","journal-title":"In ICAART"},{"issue":"2","key":"9985_CR3","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10462-012-9368-5","volume":"43","author":"C-N Anagnostopoulos","year":"2015","unstructured":"Anagnostopoulos, C.-N., Iliou, T., & Giannoukos, I. (2015). Features and classifiers for emotion recognition from speech: A survey from 2000 to 2011. Artificial Intelligence Review, 43(2), 155\u2013177.","journal-title":"Artificial Intelligence Review"},{"key":"9985_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.104886","volume":"184","author":"A Bhavan","year":"2019","unstructured":"Bhavan, A., Chauhan, P., Shah, R. R., et al. (2019). Bagged support vector machines for emotion recognition from speech. Knowledge-Based Systems, 184, 104886.","journal-title":"Knowledge-Based Systems"},{"key":"9985_CR5","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. Information Sciences, 509, 150\u2013163.","journal-title":"Information Sciences"},{"issue":"1","key":"9985_CR6","doi-asserted-by":"publisher","first-page":"65","DOI":"10.20532\/cit.2016.1002500","volume":"24","author":"JJ Christopher","year":"2016","unstructured":"Christopher, J. J., Nehemiah, K. H., & Arputharaj, K. (2016). Knowledge-based systems and interestingness measures: Analysis with clinical datasets. Journal of Computing and Information Technology, 24(1), 65\u201378.","journal-title":"Journal of Computing and Information Technology"},{"key":"9985_CR7","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., & Praveena, M. A. (2020). Multimodal speech emotion recognition and classification using convolutional neural network techniques. International Journal of Speech Technology, 23, 381\u2013388.","journal-title":"International Journal of Speech Technology"},{"issue":"1","key":"9985_CR8","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s11042-019-08222-8","volume":"79","author":"F Daneshfar","year":"2020","unstructured":"Daneshfar, F., & Kabudian, S. J. (2020). Speech emotion recognition using discriminative dimension reduction by employing a modified quantum-behaved particle swarm optimization algorithm. Multimedia Tools and Applications, 79(1), 1261\u20131289.","journal-title":"Multimedia Tools and Applications"},{"issue":"1","key":"9985_CR9","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10772-020-09776-x","volume":"24","author":"M Gomathy","year":"2021","unstructured":"Gomathy, M. (2021). Optimal feature selection for speech emotion recognition using enhanced cat swarm optimization algorithm. International Journal of Speech Technology, 24(1), 155\u2013163.","journal-title":"International Journal of Speech Technology"},{"key":"9985_CR10","doi-asserted-by":"crossref","unstructured":"Gupta, K., Gupta, M., Christopher, J., & Arunachalam, V. (2020). Fuzzy system for facial emotion recognition. In International conference on intelligent systems design and applications (pp. 536\u2013552). Springer.","DOI":"10.1007\/978-3-030-71187-0_50"},{"key":"9985_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.101894","volume":"59","author":"D Issa","year":"2020","unstructured":"Issa, D., Demirci, M. F., & Yazici, A. (2020). Speech emotion recognition with deep convolutional neural networks. Biomedical Signal Processing and Control, 59, 101894.","journal-title":"Biomedical Signal Processing and Control"},{"key":"9985_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","volume":"71","author":"Y Jadoul","year":"2018","unstructured":"Jadoul, Y., Thompson, B., & De Boer, B. (2018). Introducing parselmouth: A python interface to praat. Journal of Phonetics, 71, 1\u201315.","journal-title":"Journal of Phonetics"},{"key":"9985_CR13","doi-asserted-by":"publisher","first-page":"102681","DOI":"10.1016\/j.bspc.2021.102681","volume":"69","author":"R Kavya","year":"2021","unstructured":"Kavya, R., Christopher, J., Panda, S., & Lazarus, Y. B. (2021). Machine learning and XAI approaches for allergy diagnosis. Biomedical Signal Processing and Control, 69, 102681.","journal-title":"Biomedical Signal Processing and Control"},{"issue":"1","key":"9985_CR14","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/s10772-020-09672-4","volume":"23","author":"A Koduru","year":"2020","unstructured":"Koduru, A., Valiveti, H. B., & Budati, A. K. (2020). Feature extraction algorithms to improve the speech emotion recognition rate. International Journal of Speech Technology, 23(1), 45\u201355.","journal-title":"International Journal of Speech Technology"},{"issue":"4","key":"9985_CR15","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3233\/FI-2010-288","volume":"101","author":"MB Kursa","year":"2010","unstructured":"Kursa, M. B., Jankowski, A., & Rudnicki, W. R. (2010). Boruta\u2014a system for feature selection. Fundamenta Informaticae, 101(4), 271\u2013285.","journal-title":"Fundamenta Informaticae"},{"key":"9985_CR16","doi-asserted-by":"crossref","unstructured":"Kwon, O.-W., Chan, K., Hao, J., & Lee, T.-W. (2003). Emotion recognition by speech signals. In Eighth European conference on speech communication and technology.","DOI":"10.21437\/Eurospeech.2003-80"},{"issue":"12","key":"9985_CR17","doi-asserted-by":"publisher","first-page":"2133","DOI":"10.3390\/math8122133","volume":"8","author":"S Kwon","year":"2020","unstructured":"Kwon, S., et al. (2020). CLSTM: Deep feature-based speech emotion recognition using the hierarchical convLSTM network. Mathematics, 8(12), 2133.","journal-title":"Mathematics"},{"key":"9985_CR18","doi-asserted-by":"publisher","first-page":"114177","DOI":"10.1016\/j.eswa.2020.114177","volume":"167","author":"S Kwon","year":"2021","unstructured":"Kwon, S., et al. (2021). Mlt-dnet: Speech emotion recognition using 1d dilated CNN based on multi-learning trick approach. Expert Systems with Applications, 167, 114177.","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"9985_CR19","first-page":"559","volume":"18","author":"G Lema\u00eetre","year":"2017","unstructured":"Lema\u00eetre, G., Nogueira, F., & Aridas, C. K. (2017). Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning. The Journal of Machine Learning Research, 18(1), 559\u2013563.","journal-title":"The Journal of Machine Learning Research"},{"key":"9985_CR20","unstructured":"Liu, G.\u00a0K. (2018). Evaluating gammatone frequency cepstral coefficients with neural networks for emotion recognition from speech. arXiv preprint arXiv:1806.09010."},{"issue":"5","key":"9985_CR21","doi-asserted-by":"publisher","first-page":"e0196391","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":"9985_CR22","doi-asserted-by":"crossref","unstructured":"McFee, B., Raffel, C., Liang, D., Ellis, D. P., McVicar, M., Battenberg, E., & Nieto, O. (2015). Librosa: Audio and music signal analysis in python. In Proceedings of the 14th python in science conference Vol. 8, (pp. 18\u201325). Citeseer.","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"9985_CR23","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) (pp. 41\u201344). IEEE.","DOI":"10.1109\/ECTI-CON49241.2020.9158221"},{"issue":"2","key":"9985_CR24","first-page":"101","volume":"6","author":"Y Pan","year":"2012","unstructured":"Pan, Y., Shen, P., & Shen, L. (2012). Speech emotion recognition using support vector machine. International Journal of Smart Home, 6(2), 101\u2013108.","journal-title":"International Journal of Smart Home"},{"key":"9985_CR25","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al. (2011). Scikit-learn: Machine learning in python. The Journal of Machine Learning Research, 12, 2825\u20132830.","journal-title":"The Journal of Machine Learning Research"},{"issue":"8","key":"9985_CR26","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","volume":"27","author":"H Peng","year":"2005","unstructured":"Peng, H., Long, F., & Ding, C. (2005). Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1226\u20131238.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9985_CR27","doi-asserted-by":"crossref","unstructured":"Petrushin, V. A. (2000). Emotion recognition in speech signal: Experimental study, development, and application. In Sixth international conference on spoken language processing.","DOI":"10.21437\/ICSLP.2000-791"},{"key":"9985_CR28","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001","volume-title":"Affective computing","author":"RW Picard","year":"2000","unstructured":"Picard, R. W. (2000). Affective computing. MIT press."},{"issue":"4","key":"9985_CR29","doi-asserted-by":"publisher","first-page":"172988141771983","DOI":"10.1177\/1729881417719836","volume":"14","author":"C Quan","year":"2017","unstructured":"Quan, C., Zhang, B., Sun, X., & Ren, F. (2017). A combined cepstral distance method for emotional speech recognition. International Journal of Advanced Robotic Systems, 14(4), 1729881417719836.","journal-title":"International Journal of Advanced Robotic Systems"},{"key":"9985_CR30","doi-asserted-by":"crossref","unstructured":"Rojas, R. (1996). The backpropagation algorithm. In Neural networks (pp. 149\u2013182). Springer.","DOI":"10.1007\/978-3-642-61068-4_7"},{"issue":"3","key":"9985_CR31","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/j.ipm.2008.09.003","volume":"45","author":"J Rong","year":"2009","unstructured":"Rong, J., Li, G., & Chen, Y.-P.P. (2009). Acoustic feature selection for automatic emotion recognition from speech. Information Processing & Management, 45(3), 315\u2013328.","journal-title":"Information Processing & Management"},{"key":"9985_CR32","doi-asserted-by":"crossref","unstructured":"Shegokar, P., & Sircar, P. (2016). Continuous wavelet transform based speech emotion recognition. In 2016 10th international conference on signal processing and communication systems (ICSPCS) (pp. 1\u20138). IEEE.","DOI":"10.1109\/ICSPCS.2016.7843306"},{"key":"9985_CR33","doi-asserted-by":"crossref","unstructured":"Surampudi, N., Srirangan, M., & Christopher, J. (2019). Enhanced feature extraction approaches for detection of sound events. In 2019 IEEE 9th international conference on advanced computing (IACC) (pp. 223\u2013229). IEEE.","DOI":"10.1109\/IACC48062.2019.8971574"},{"key":"9985_CR34","doi-asserted-by":"crossref","unstructured":"Tzirakis, P., Zhang, J., & Schuller, B. W. (2018). End-to-end speech emotion recognition using deep neural networks. In 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 5089\u20135093). IEEE.","DOI":"10.1109\/ICASSP.2018.8462677"},{"key":"9985_CR35","unstructured":"Vogt, T., & Andr\u00e9, E. (2006). Improving automatic emotion recognition from speech via gender differentiaion. In LREC (pp. 1123\u20131126)."},{"key":"9985_CR36","doi-asserted-by":"crossref","unstructured":"Zamil, A. A. A., Hasan, S., Baki, S. M. J., Adam, J. M., & 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) (pp. 281\u2013285). IEEE.","DOI":"10.1109\/ICREST.2019.8644168"},{"issue":"3","key":"9985_CR37","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. Multimedia Tools and Applications, 78(3), 3705\u20133722.","journal-title":"Multimedia Tools and Applications"},{"key":"9985_CR38","doi-asserted-by":"crossref","unstructured":"Zhou, X., Garcia-Romero, D., Duraiswami, R., Espy-Wilson, C., & Shamma, S. (2011). Linear versus mel frequency cepstral coefficients for speaker recognition. In 2011 IEEE workshop on automatic speech recognition & understanding (pp. 559\u2013564). IEEE.","DOI":"10.1109\/ASRU.2011.6163888"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09985-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-022-09985-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-09985-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,10]],"date-time":"2022-08-10T07:44:56Z","timestamp":1660117496000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-022-09985-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,8]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["9985"],"URL":"https:\/\/doi.org\/10.1007\/s10772-022-09985-6","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,8]]},"assertion":[{"value":"16 April 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}