{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T06:03:19Z","timestamp":1781589799989,"version":"3.54.5"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012632","name":"Nazarbayev University Faculty Development Competitive Research Grant","doi-asserted-by":"publisher","award":["021220FD1151"],"award-info":[{"award-number":["021220FD1151"]}],"id":[{"id":"10.13039\/501100012632","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012632","name":"Nazarbayev University Faculty Development Competitive Research Grant","doi-asserted-by":"publisher","award":["20122022FD4120"],"award-info":[{"award-number":["20122022FD4120"]}],"id":[{"id":"10.13039\/501100012632","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3287093","type":"journal-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T17:30:39Z","timestamp":1686936639000},"page":"61950-61957","source":"Crossref","is-referenced-by-count":14,"title":["On the Effect of Log-Mel Spectrogram Parameter Tuning for Deep Learning-Based Speech Emotion Recognition"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5190-6847","authenticated-orcid":false,"given":"Azamat","family":"Mukhamediya","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3397-0647","authenticated-orcid":false,"given":"Siamac","family":"Fazli","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9172-8413","authenticated-orcid":false,"given":"Amin","family":"Zollanvari","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, School of Engineering and Digital Sciences, Nazarbayev University, Astana, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3171965"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/s21227530"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2020.102763"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11091328"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1811"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2927384"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054073"},{"key":"ref31","first-page":"3","author":"feurer","year":"2019","journal-title":"Hyperparameter Optimization"},{"key":"ref30","first-page":"161","article-title":"Speech database development: Design and analysis of the acoustic-phonetic corpus","author":"lamel","year":"1989","journal-title":"Proc Speech Input\/Output Assessment Speech Databases"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3163856"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref32","first-page":"234","article-title":"A C-LSTM with attention mechanism for question categorization","author":"ashok kumar","year":"2020","journal-title":"Machine Learning and Metaheuristics Algorithms and Applications"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC51323.2021.9498861"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3043201"},{"key":"ref17","article-title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and ¡0.5mb model size","author":"iandola","year":"2016","journal-title":"arXiv 1602 07360"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-018-0960-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-021-00208-5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107316"},{"key":"ref19","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"1","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref18","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc 3rd Int Conf Learn Represent (ICLR)"},{"key":"ref24","author":"huang","year":"2001","journal-title":"Spoken Language Processing A Guide to Theory Algorithm and System Development"},{"key":"ref23","first-page":"109","author":"o\u2019shaughnessy","year":"2000","journal-title":"Hearing"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-446"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-374490-6.00007-6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3067460"},{"key":"ref27","first-page":"398","author":"haq","year":"2010","journal-title":"Machine Audition Principles Algorithms and Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2788044"},{"key":"ref7","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/app10134653"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-015-9388-2"},{"key":"ref6","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume":"48","author":"amodei","year":"2016","journal-title":"Proc 33rd Int Conf Int Conf Mach Learn (ICML)"},{"key":"ref5","article-title":"Escaping the big data paradigm with compact transformers","author":"hassani","year":"2021","journal-title":"arXiv 2104 05704"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.005"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10154046.pdf?arnumber=10154046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T19:29:38Z","timestamp":1689017378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10154046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3287093","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}