{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T01:32:50Z","timestamp":1768354370542,"version":"3.49.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T00:00:00Z","timestamp":1599523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,8]],"date-time":"2020-09-08T00:00:00Z","timestamp":1599523200000},"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":[[2020,12]]},"DOI":"10.1007\/s10772-020-09690-2","type":"journal-article","created":{"date-parts":[[2020,9,10]],"date-time":"2020-09-10T07:41:14Z","timestamp":1599723674000},"page":"799-806","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["Pattern recognition and features selection for speech emotion recognition model using deep learning"],"prefix":"10.1007","volume":"23","author":[{"given":"Kittisak","family":"Jermsittiparsert","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdurrahman","family":"Abdurrahman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parinya","family":"Siriattakul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ludmila A.","family":"Sundeeva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wahidah","family":"Hashim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robbi","family":"Rahim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andino","family":"Maseleno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,8]]},"reference":[{"key":"9690_CR1","unstructured":"Cak\u0131r, E., Heittola, T., & Virtanen, T. (2016). Domestic audio tagging with convolutional neural networks. In IEEE AASP challenge on detection and classification of acoustic scenes and events (DCASE 2016), (pp. 1\u20132)."},{"issue":"6","key":"9690_CR2","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TASLP.2017.2690575","volume":"25","author":"E Cak\u0131r","year":"2017","unstructured":"Cak\u0131r, E., Parascandolo, G., Heittola, T., Huttunen, H., & Virtanen, T. (2017). Convolutional recurrent neural networks for polyphonic sound event detection. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 25(6), 1291\u20131303.","journal-title":"IEEE\/ACM Transactions on Audio, Speech, and Language Processing"},{"key":"9690_CR3","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, (pp. 1251\u20131258).","DOI":"10.1109\/CVPR.2017.195"},{"issue":"3","key":"9690_CR4","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M. S., & Karray, F. (2011). Survey on speech emotion recognition: Features, classification schemes, and databases. Pattern Recognition, 44(3), 572\u2013587.","journal-title":"Pattern Recognition"},{"key":"9690_CR5","doi-asserted-by":"crossref","unstructured":"Hershey, S., Chaudhuri, S., Ellis, D.P., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., & Seybold, B. et al. (2017). CNN architectures for largescale audio classification. In 2017 IEEE international conference on acoustics, speech and signal processing (ICASSP), (pp. 131\u2013135). IEEE.","DOI":"10.1109\/ICASSP.2017.7952132"},{"issue":"2","key":"9690_CR6","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/s10772-011-9125-1","volume":"15","author":"SG Koolagudi","year":"2012","unstructured":"Koolagudi, S. G., & Rao, K. S. (2012). Emotion recognition from speech: A review. International Journal of Speech Technology, 15(2), 99\u2013117.","journal-title":"International Journal of Speech Technology"},{"key":"9690_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s11554-019-00879-6","author":"N Krishnaraj","year":"2019","unstructured":"Krishnaraj, N., Elhoseny, M., Thenmozhi, M., Selim, M. M., & Shankar, K. (2019). Deep learning model for real-time image compression in Internet of Underwater Things (IoUT). Journal of Real-Time Image Processing. https:\/\/doi.org\/10.1007\/s11554-019-00879-6.","journal-title":"Journal of Real-Time Image Processing"},{"key":"9690_CR8","doi-asserted-by":"publisher","first-page":"105487","DOI":"10.1016\/j.asoc.2019.105487","volume":"81","author":"SK Lakshmanaprabu","year":"2019","unstructured":"Lakshmanaprabu, S. K., Mohanty, S. N., Krishnamoorthy, S., Uthayakumar, J., & Shankar, K. (2019a). Online clinical decision support system using optimal deep neural networks. Applied Soft Computing, 81, 105487.","journal-title":"Applied Soft Computing"},{"key":"9690_CR9","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.future.2018.10.009","volume":"92","author":"SK Lakshmanaprabu","year":"2019","unstructured":"Lakshmanaprabu, S. K., Mohanty, S. N., Shankar, K., Arunkumar, N., & Ramirez, G. (2019b). Optimal deep learning model for classification of lung cancer on CT images. Future Generation Computer Systems, 92, 374\u2013382.","journal-title":"Future Generation Computer Systems"},{"issue":"7553","key":"9690_CR10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436.","journal-title":"Nature"},{"key":"9690_CR11","first-page":"66","volume":"10","author":"E Lydia","year":"2019","unstructured":"Lydia, E., Moses, G., Sharmili, N., Shankar, K., & Maseleno, A. (2019). Image classification using deep neural networks for malaria disease detection. International Journal on Emerging Technologies, 10, 66\u201370.","journal-title":"International Journal on Emerging Technologies"},{"issue":"4","key":"9690_CR12","doi-asserted-by":"publisher","first-page":"270","DOI":"10.15598\/aeee.v10i4.738","volume":"10","author":"P Partila","year":"2012","unstructured":"Partila, P., Voznak, M., Mikulec, M., & Zdralek, J. (2012). Fundamental frequency extraction method using central clipping and its importance for the classification of emotional state. Advances in Electrical and Electronic Engineering, 10(4), 270\u2013275.","journal-title":"Advances in Electrical and Electronic Engineering"},{"key":"9690_CR14","doi-asserted-by":"crossref","unstructured":"Shankar, K., Manickam, P., Devika, G., & Ilayaraja, M. (2018, December). Optimal feature selection for chronic kidney disease classification using deep learning classifier. In 2018 IEEE international conference on computational intelligence and computing research (ICCIC) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ICCIC.2018.8782340"},{"issue":"5","key":"9690_CR15","first-page":"114","volume":"8","author":"M Voznak","year":"2010","unstructured":"Voznak, M., Rezac, F., & Rozhon, J. (2010). Speech quality monitoring in Czech national research network. Advances in Electrical and Electronic Engineering, 8(5), 114\u2013117.","journal-title":"Advances in Electrical and Electronic Engineering"},{"key":"9690_CR16","doi-asserted-by":"crossref","unstructured":"Zarkowski, M. (2013). Identification-driven emotion recognition system for a social robot. In Proceedings of the 18th international conference on methods and models in automation and robotics (MMAR\u201913), August 2013 (pp. 138\u2013143).","DOI":"10.1109\/MMAR.2013.6669895"},{"key":"9690_CR17","unstructured":"Zhang, L., & Han, J. (2019). Acoustic scene classification using multi-layer temporal pooling based on convolutional neural network. arXiv:1902.10063."}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09690-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-020-09690-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-020-09690-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T23:29:45Z","timestamp":1631057385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-020-09690-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,8]]},"references-count":16,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["9690"],"URL":"https:\/\/doi.org\/10.1007\/s10772-020-09690-2","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,8]]},"assertion":[{"value":"12 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}