{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T22:34:46Z","timestamp":1771022086276,"version":"3.50.1"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T00:00:00Z","timestamp":1619049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T00:00:00Z","timestamp":1619049600000},"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":[[2021,9]]},"DOI":"10.1007\/s10772-021-09838-8","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T15:04:54Z","timestamp":1619103894000},"page":"625-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Language dialect based speech emotion recognition through deep learning techniques"],"prefix":"10.1007","volume":"24","author":[{"given":"Sukumar","family":"Rajendran","sequence":"first","affiliation":[]},{"given":"Sandeep Kumar","family":"Mathivanan","sequence":"additional","affiliation":[]},{"given":"Prabhu","family":"Jayagopal","sequence":"additional","affiliation":[]},{"given":"Maheshwari","family":"Venkatasen","sequence":"additional","affiliation":[]},{"given":"Thanapal","family":"Pandi","sequence":"additional","affiliation":[]},{"given":"Manivannan","family":"Sorakaya Somanathan","sequence":"additional","affiliation":[]},{"given":"Muthamilselvan","family":"Thangaval","sequence":"additional","affiliation":[]},{"given":"Prasanna","family":"Mani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,22]]},"reference":[{"key":"9838_CR1","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","volume":"116","author":"MB Ak\u00e7ay","year":"2020","unstructured":"Ak\u00e7ay, M. B., & O\u011fuz, K. (2020). Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Communication, 116, 56\u201376.","journal-title":"Speech Communication"},{"issue":"2","key":"9838_CR2","first-page":"1","volume":"79","author":"A Bakhshi","year":"2020","unstructured":"Bakhshi, A., Chalup, S., Harimi, A., & Mirhassani, S. M. (2020). Recognition of emotion from speech using evolutionary cepstral coefficients. Multimedia Tools and Applications, 79(2), 1\u201321.","journal-title":"Multimedia Tools and Applications"},{"issue":"1","key":"9838_CR3","doi-asserted-by":"publisher","first-page":"264","DOI":"10.3758\/s13428-019-01223-3","volume":"52","author":"M Bernard","year":"2020","unstructured":"Bernard, M., Thiolliere, R., Saksida, A., Loukatou, G. R., Larsen, E., Johnson, M., Fibla, L., Dupoux, E., Daland, R., Cao, X. N., et al. (2020). WordSeg: Standardizing unsupervised word form segmentation from text. Behavior Research Methods, 52(1), 264\u2013278.","journal-title":"Behavior Research Methods"},{"key":"9838_CR4","doi-asserted-by":"crossref","unstructured":"Christy, A., Vaithyasubramanian, S., Jesudoss, A., & Praveena, M. D. A. (2020). Multimodal speech emotion recognition and classification using convolutional neural network techniques. International Journal of Speech Technology, 23, 381\u2013388 (2020)","DOI":"10.1007\/s10772-020-09713-y"},{"key":"9838_CR5","doi-asserted-by":"crossref","unstructured":"Gaonkar, R., Kwon, H., Bastan, M., Balasubramanian, N., & Chambers, N. (2020). Modeling Label Semantics for Predicting Emotional Reactions. ArXiv Preprint. arXiv:2006.05489.","DOI":"10.18653\/v1\/2020.acl-main.426"},{"key":"9838_CR6","unstructured":"Grave, E., Bojanowski, P., Gupta, P., Joulin, A., & Mikolov, T. (2018). Learning word vectors for 157 languages. In Proceedings of the international conference on language resources and evaluation (LREC 2018)."},{"issue":"4","key":"9838_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10772-020-09690-2","volume":"23","author":"K Jermsittiparsert","year":"2020","unstructured":"Jermsittiparsert, K., Abdurrahman, A., Siriattakul, P., Sundeeva, L. A., Hashim, W., Rahim, R., & Maseleno, A. (2020). Pattern recognition and features selection for speech emotion recognition model using deep learning. International Journal of Speech Technology, 23(4), 1\u20138.","journal-title":"International Journal of Speech Technology"},{"key":"9838_CR8","unstructured":"Kunchukuttan, A., Kakwani, D., Golla, S., Gokul, N. C., Bhattacharyya, A., Khapra, M. M., & Kumar, P. (2020). AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages. ArXiv Preprint. arXiv:2005.00085."},{"issue":"3","key":"9838_CR9","first-page":"55","volume":"6","author":"AM Moselhy","year":"2013","unstructured":"Moselhy, A. M., & Abdelnaiem, A. A. (2013). LPC and MFCC performance evaluation with artificial neural network for spoken language identification. International Journal of Signal Processing, Image Processing and Pattern Recognition, 6(3), 55.","journal-title":"International Journal of Signal Processing, Image Processing and Pattern Recognition"},{"issue":"2","key":"9838_CR10","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s10772-020-09687-x","volume":"23","author":"S Rajendran","year":"2020","unstructured":"Rajendran, S., & Jayagopal, P. (2020). Preserving learnability and intelligibility at the point of care with assimilation of different speech recognition techniques. International Journal of Speech Technology, 23(2), 265\u2013276. https:\/\/doi.org\/10.1007\/s10772-020-09687-x.","journal-title":"International Journal of Speech Technology"},{"key":"9838_CR11","doi-asserted-by":"crossref","unstructured":"Shi, Y., Hwang, M.-Y., & Lei, X. (2019). End-to-end speech recognition using a high rank lstm-ctc based model. In ICASSP 2019\u20132019 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 7080\u20137084).","DOI":"10.1109\/ICASSP.2019.8683297"},{"key":"9838_CR12","doi-asserted-by":"crossref","unstructured":"Shivaprasad, S., & Sadanandam, M. (2020). Identification of regional dialects of Telugu language using text independent speech processing models. International Journal of Speech Technology, 23, 251\u2013258 (2020).","DOI":"10.1007\/s10772-020-09678-y"},{"key":"9838_CR13","unstructured":"Stiennon, N., Ouyang, L., Wu, J., Ziegler, D. M., Lowe, R., Voss, C., Radford, A., Amodei, D., & Christiano, P. (2020). Learning to summarize from human feedback. ArXiv Preprint. arXiv:2009.01325."},{"key":"9838_CR14","unstructured":"Tavares, A. R., Avelar, P., Flach, J. M., Nicolau, M., Lamb, L. C., & Vardi, M. (2020). Understanding Boolean function learnability on deep neural networks. ArXiv Preprint. arXiv:2009.05908"},{"key":"9838_CR15","doi-asserted-by":"crossref","unstructured":"Xu, Q., Likhomanenko, T., Kahn, J., Hannun, A., Synnaeve, G., & Collobert, R. (2020). Iterative pseudo-labeling for speech recognition. Computation and Language. arXiv Preprint. arXiv:2005.09267.","DOI":"10.21437\/Interspeech.2020-1800"},{"key":"9838_CR16","doi-asserted-by":"crossref","unstructured":"Yang, Y., Yuan, S., Cer, D., Kong, S.-Y., Constant, N., Pilar, P., Ge, H., Sung, Y.-H., Strope, B., & Kurzweil, R. (2018). Learning semantic textual similarity from conversations. ArXiv Preprint. arXiv:1804.07754.","DOI":"10.18653\/v1\/W18-3022"},{"key":"9838_CR17","doi-asserted-by":"crossref","unstructured":"Yoon, S., Byun, S., & Jung, K. (2018). Multimodal speech emotion recognition using audio and text. In 2018 IEEE spoken language technology workshop (SLT) (pp. 112\u2013118).","DOI":"10.1109\/SLT.2018.8639583"},{"key":"9838_CR18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3020421","author":"C Yu","year":"2020","unstructured":"Yu, C., Kang, M., Chen, Y., Wu, J., & Zhao, X. (2020). Acoustic modeling based on deep learning for low-resource speech recognition: An overview. IEEE Access. https:\/\/doi.org\/10.1109\/ACCESS.2020.3020421.","journal-title":"IEEE Access"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09838-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09838-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09838-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T11:33:31Z","timestamp":1629200011000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09838-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,22]]},"references-count":18,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["9838"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09838-8","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,22]]},"assertion":[{"value":"28 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}