{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T19:46:48Z","timestamp":1770580008462,"version":"3.49.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T00:00:00Z","timestamp":1610496000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T00:00:00Z","timestamp":1610496000000},"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":[[2021,6]]},"DOI":"10.1007\/s10772-020-09792-x","type":"journal-article","created":{"date-parts":[[2021,1,14]],"date-time":"2021-01-14T03:15:18Z","timestamp":1610594118000},"page":"303-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":81,"title":["Fusion of mel and gammatone frequency cepstral coefficients for speech emotion recognition using deep C-RNN"],"prefix":"10.1007","volume":"24","author":[{"given":"U.","family":"Kumaran","sequence":"first","affiliation":[]},{"given":"S.","family":"Radha Rammohan","sequence":"additional","affiliation":[]},{"given":"Senthil Murugan","family":"Nagarajan","sequence":"additional","affiliation":[]},{"given":"A.","family":"Prathik","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,1,13]]},"reference":[{"key":"9792_CR1","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., & Dean, J. et al. (2016). Tensorflow: A system for large-scale machine learning. In\u00a012th {USENIX} symposium on operating systems design and implementation ({OSDI} 16)\u00a0(pp. 265\u2013283)."},{"issue":"2","key":"9792_CR2","first-page":"285","volume":"33","author":"K Aghajani","year":"2020","unstructured":"Aghajani, K., & Esmaili Paeen Afrakoti, I. (2020). Speech emotion recognition using scalogram based deep structure. International Journal of Engineering, 33(2), 285\u2013292.","journal-title":"International Journal of Engineering"},{"key":"9792_CR3","doi-asserted-by":"crossref","unstructured":"Bhavan, A., Sharma, M., Piplani, M., Chauhan, P., & Shah, R. R. (2020). Deep learning approaches for speech emotion recognition. In\u00a0Deep learning-based approaches for sentiment analysis\u00a0(pp. 259\u2013289). Springer, Singapore.","DOI":"10.1007\/978-981-15-1216-2_10"},{"issue":"2","key":"9792_CR4","doi-asserted-by":"crossref","first-page":"90","DOI":"10.22452\/mjcs.vol33no2.1","volume":"33","author":"H Bourouba","year":"2020","unstructured":"Bourouba, H., & Djemili, R. (2020). Feature extraction algorithm using new cepstral techniques for robust speech recognition. Malaysian Journal of Computer Science, 33(2), 90\u2013101.","journal-title":"Malaysian Journal of Computer Science"},{"key":"9792_CR5","doi-asserted-by":"publisher","unstructured":"Cheng, H., & Tang, X. (2020). Speech emotion recognition based on interactive convolutional neural network. 2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP). https:\/\/doi.org\/10.1109\/icicsp50920.2020.9232071.","DOI":"10.1109\/icicsp50920.2020.9232071"},{"key":"9792_CR6","doi-asserted-by":"publisher","unstructured":"Delbrouck, J., Tits, N., Brousmiche, M., & Dupont, S. (2020). A transformer-based joint-encoding for emotion recognition and sentiment analysis. Second grand-challenge and workshop on multimodal language (Challenge-HML). https:\/\/doi.org\/10.18653\/v1\/2020.challengehml-1.1.","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"issue":"8","key":"9792_CR7","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 Computing and Applications, 29(8), 59\u201366.","journal-title":"Neural Computing and Applications"},{"issue":"2","key":"9792_CR8","first-page":"170","volume":"17","author":"L Deng","year":"2020","unstructured":"Deng, L., & Gao, Y. (2020). Gammachirp filter banks applied in roust speaker recognition based on GMM-UBM classifier. Int. Arab J. Inf. Technol., 17(2), 170\u2013177.","journal-title":"Int. Arab J. Inf. Technol."},{"key":"9792_CR9","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.neucom.2017.01.120","volume":"326","author":"D Griol","year":"2019","unstructured":"Griol, D., Molina, J. M., & Callejas, Z. (2019). Combining speech-based and linguistic classifiers to recognize emotion in user spoken utterances. Neurocomputing, 326, 132\u2013140.","journal-title":"Neurocomputing"},{"key":"9792_CR10","doi-asserted-by":"crossref","unstructured":"Gu, Y., Li, X., Chen, S., Zhang, J., & Marsic, I. (2017). Speech intention classification with multimodal deep learning. In\u00a0Canadian conference on artificial intelligence\u00a0(pp. 260\u2013271). Cham: Springer.","DOI":"10.1007\/978-3-319-57351-9_30"},{"key":"9792_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2020.3003648","author":"W Guo","year":"2020","unstructured":"Guo, W., Zhang, Y., Cai, X., Meng, L., Yang, J., & Yuan, X. (2020). LD-MAN: Layout-driven multimodal attention network for online news sentiment recognition. IEEE Transactions on Multimedia. https:\/\/doi.org\/10.1109\/tmm.2020.3003648.","journal-title":"IEEE Transactions on Multimedia"},{"key":"9792_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, S., & Mehra, A. (2015). Speech emotion recognition using svm with thresholding fusion. In\u00a02015 2nd International Conference on Signal Processing and Integrated Networks (SPIN)\u00a0(pp. 570\u2013574). IEEE.","DOI":"10.1109\/SPIN.2015.7095427"},{"key":"9792_CR13","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.neucom.2020.01.048","volume":"391","author":"M Hao","year":"2020","unstructured":"Hao, M., Cao, W., Liu, Z., Wu, M., & Xiao, P. (2020). Visual-audio emotion recognition based on multi-task and ensemble learning with multiple features. Neurocomputing, 391, 42\u201351. https:\/\/doi.org\/10.1016\/j.neucom.2020.01.048.","journal-title":"Neurocomputing"},{"key":"9792_CR14","doi-asserted-by":"crossref","unstructured":"Houjeij, A., Hamieh, L., Mehdi, N., & Hajj, H. (2012). A novel approach for emotion classification based on fusion of text and speech. In\u00a02012 19th International Conference on Telecommunications (ICT)\u00a0(pp. 1\u20136). IEEE.","DOI":"10.1109\/ICTEL.2012.6221211"},{"key":"9792_CR15","doi-asserted-by":"publisher","first-page":"90368","DOI":"10.1109\/ACCESS.2019.2927384","volume":"7","author":"P Jiang","year":"2019","unstructured":"Jiang, P., Fu, H., Tao, H., Lei, P., & Zhao, L. (2019). Parallelized convolutional recurrent neural network with spectral features for speech emotion recognition. IEEE Access, 7, 90368\u201390377.","journal-title":"IEEE Access"},{"key":"9792_CR16","doi-asserted-by":"crossref","unstructured":"Koo, H., Jeong, S., Yoon, S., & Kim, W. (2020). Development of speech emotion recognition algorithm using MFCC and prosody. In 2020 International Conference on Electronics, Information, and Communication (ICEIC) (pp. 1\u20134). IEEE.","DOI":"10.1109\/ICEIC49074.2020.9051281"},{"key":"9792_CR17","unstructured":"Krishna, G., Tran, C., Carnahan, M., Hagood, M. M., & Tewfik, A. H. (2020). Speech recognition using EEG signals recorded using dry electrodes.\u00a0arXiv preprint arXiv:abs\/2008.07621."},{"key":"9792_CR18","first-page":"28","volume":"2018","author":"CW Lee","year":"2018","unstructured":"Lee, C. W., Song, K. Y., Jeong, J., & Choi, W. Y. (2018). Convolutional attention networks for multimodal emotion recognition from speech and text data. ACL, 2018, 28.","journal-title":"ACL"},{"issue":"5","key":"9792_CR19","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":"9792_CR20","doi-asserted-by":"crossref","unstructured":"Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., & Manocha, D. (2020). M3ER: Multiplicative multimodal emotion recognition using facial, textual, and speech cues. In\u00a0AAAI\u00a0(pp. 1359\u20131367).","DOI":"10.1609\/aaai.v34i02.5492"},{"issue":"2","key":"9792_CR21","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1007\/s11277-018-5513-z","volume":"103","author":"NS Murugan","year":"2018","unstructured":"Murugan, N. S., & Devi, G. U. (2018a). Detecting streaming of Twitter spam using hybrid method. Wireless Personal Communications, 103(2), 1353\u20131374.","journal-title":"Wireless Personal Communications"},{"issue":"1","key":"9792_CR22","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1504\/IJEWM.2018.091308","volume":"21","author":"NS Murugan","year":"2018","unstructured":"Murugan, N. S., & Devi, G. U. (2018b). Detecting spams in social networks using ML algorithms-a review. International Journal of Environment and Waste Management, 21(1), 22\u201336.","journal-title":"International Journal of Environment and Waste Management"},{"issue":"6","key":"9792_CR23","doi-asserted-by":"publisher","first-page":"13965","DOI":"10.1007\/s10586-018-2158-3","volume":"22","author":"NS Murugan","year":"2019","unstructured":"Murugan, N. S., & Devi, G. U. (2019). Feature extraction using LR-PCA hybridization on twitter data and classification accuracy using machine learning algorithms. Cluster Computing, 22(6), 13965\u201313974.","journal-title":"Cluster Computing"},{"issue":"5","key":"9792_CR24","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1007\/s00521-018-3476-3","volume":"31","author":"SM Nagarajan","year":"2019","unstructured":"Nagarajan, S. M., & Gandhi, U. D. (2019). Classifying streaming of Twitter data based on sentiment analysis using hybridization. Neural Computing and Applications, 31(5), 1425\u20131433.","journal-title":"Neural Computing and Applications"},{"key":"9792_CR25","doi-asserted-by":"crossref","unstructured":"Sahay, S., Kumar, S. H., Xia, R., Huang, J., & Nachman, L. (2018). Multimodal relational tensor network for sentiment and emotion classification.\u00a0arXiv preprint arXiv:abs\/1806.02923.","DOI":"10.18653\/v1\/W18-3303"},{"issue":"1","key":"9792_CR26","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1007\/s13278-018-0505-2","volume":"8","author":"K Sailunaz","year":"2018","unstructured":"Sailunaz, K., Dhaliwal, M., Rokne, J., & Alhajj, R. (2018). Emotion detection from text and speech: A survey. Social Network Analysis and Mining, 8(1), 28.","journal-title":"Social Network Analysis and Mining"},{"key":"9792_CR27","doi-asserted-by":"publisher","first-page":"79861","DOI":"10.1109\/ACCESS.2020.2990405","volume":"8","author":"M Sajjad","year":"2020","unstructured":"Sajjad, M., & Kwon, S. (2020). Clustering-based speech emotion recognition by incorporating learned features and deep BiLSTM. IEEE Access, 8, 79861\u201379875.","journal-title":"IEEE Access"},{"key":"9792_CR28","doi-asserted-by":"crossref","unstructured":"Shirazi, Z. A., de Souza, C. P., Kashef, R., & Rodrigues, F. F. (2020). Deep learning in the healthcare industry: theory and applications. In\u00a0Computational intelligence and soft computing applications in healthcare management science\u00a0(pp. 220\u2013245). IGI Global.","DOI":"10.4018\/978-1-7998-2581-4.ch010"},{"issue":"3","key":"9792_CR29","doi-asserted-by":"publisher","first-page":"718","DOI":"10.3390\/s20030718","volume":"20","author":"L Shu","year":"2020","unstructured":"Shu, L., Yu, Y., Chen, W., Hua, H., Li, Q., Jin, J., & Xu, X. (2020). Wearable emotion recognition using heart rate data from a smart bracelet. Sensors, 20(3), 718.","journal-title":"Sensors"},{"key":"9792_CR30","doi-asserted-by":"crossref","unstructured":"Treigys, P., Korvel, G., Tamulevi\u010dius, G., Bernatavi\u010dien\u0117, J., & Kostek, B. (2020). Investigating feature spaces for isolated word recognition. In\u00a0Data science: New issues, challenges and applications\u00a0(pp. 165\u2013181). Springer, Cham.","DOI":"10.1007\/978-3-030-39250-5_9"},{"issue":"2","key":"9792_CR32","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1109\/TASL.2012.2217129","volume":"21","author":"A Trilla","year":"2012","unstructured":"Trilla, A., & Alias, F. (2012). Sentence-based sentiment analysis for expressive text-to-speech. IEEE Transactions on Audio, Speech, and Language Processing, 21(2), 223\u2013233.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9792_CR33","doi-asserted-by":"publisher","first-page":"101756","DOI":"10.1016\/j.bspc.2019.101756","volume":"58","author":"C Wei","year":"2020","unstructured":"Wei, C., Chen, L. L., Song, Z. Z., Lou, X. G., & Li, D. D. (2020). EEG-based emotion recognition using simple recurrent units network and ensemble learning. Biomedical Signal Processing and Control, 58, 101756.","journal-title":"Biomedical Signal Processing and Control"},{"key":"9792_CR34","doi-asserted-by":"crossref","unstructured":"Wu, M., Su, W., Chen, L., Pedrycz, W., & Hirota, K. (2020). Two-stage fuzzy fusion based-convolution neural network for dynamic emotion recognition. IEEE Transactions on Affective Computing.","DOI":"10.1109\/TAFFC.2020.2966440"},{"key":"9792_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59277-6_26","author":"SN Zisad","year":"2020","unstructured":"Zisad, S. N., Hossain, M. S., & Andersson, K. (2020). Speech emotion recognition in neurological disorders using convolutional neural network. Brain Informatics Lecture Notes in Computer Science. https:\/\/doi.org\/10.1007\/978-3-030-59277-6_26.","journal-title":"Brain Informatics Lecture Notes in Computer Science"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09792-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09792-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09792-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T14:05:22Z","timestamp":1670767522000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09792-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,13]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,6]]}},"alternative-id":["9792"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09792-x","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,13]]},"assertion":[{"value":"14 September 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}