{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:50:05Z","timestamp":1774540205887,"version":"3.50.1"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100011665","name":"Deanship of Scientific Research, King Saud University","doi-asserted-by":"publisher","award":["RG-1437-018"],"award-info":[{"award-number":["RG-1437-018"]}],"id":[{"id":"10.13039\/501100011665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2980452","type":"journal-article","created":{"date-parts":[[2020,3,12]],"date-time":"2020-03-12T20:25:17Z","timestamp":1584044717000},"page":"54663-54680","source":"Crossref","is-referenced-by-count":24,"title":["Towards Deep Object Detection Techniques for Phoneme Recognition"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7962-8121","authenticated-orcid":false,"given":"Mohammed","family":"Algabri","sequence":"first","affiliation":[]},{"given":"Hassan","family":"Mathkour","sequence":"additional","affiliation":[]},{"given":"Mohamed Abdelkader","family":"Bencherif","sequence":"additional","affiliation":[]},{"given":"Mansour","family":"Alsulaiman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9478-9206","authenticated-orcid":false,"given":"Mohamed Amine","family":"Mekhtiche","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref38","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref33","author":"krasin","year":"2017","journal-title":"Openimages A public dataset for large-scale multi-label and multi-class image classification"},{"key":"ref32","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00255"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref34","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00667"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref20","first-page":"9","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref24","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112840"},{"key":"ref25","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0068-3"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-018-09584-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.4018\/jitr.2009062905"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-009-9026-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1142\/9789813229396_0001"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953168"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1898"},{"key":"ref52","article-title":"Interpretable convolutional filters with SincNet","author":"ravanelli","year":"2018","journal-title":"arXiv 1811 09725"},{"key":"ref40","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","author":"garofolo","year":"1993"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2888882"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912648"},{"key":"ref6","article-title":"Object detection in 20 years: A survey","author":"zou","year":"2019","journal-title":"arXiv 1905 05055"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref9","article-title":"Objects as points","author":"zhou","year":"2019","journal-title":"arXiv 1904 07850"},{"key":"ref46","first-page":"39","article-title":"Deep belief networks for phone recognition","author":"mohamed","year":"2009","journal-title":"Proc Workshop Deep Learn Speech Recognit Rel Appl (NIPS)"},{"key":"ref45","article-title":"Deep neural networks for acoustic modeling in speech recognition","author":"hinton","year":"0","journal-title":"IEEE Signal Process Mag"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0205355"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref41","first-page":"125","article-title":"TED-LIUM: An automatic speech recognition dedicated corpus","author":"rousseau","year":"2012","journal-title":"Proc LREC"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00794-2_47"},{"key":"ref43","first-page":"4423","article-title":"Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license","author":"korvas","year":"2014","journal-title":"Proc Int Conf Lang Res Eval (LREC)"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.11.002"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.12.020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1561\/1500000061"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/13\/5\/056004"},{"key":"ref77","first-page":"175","volume":"3","author":"young","year":"2002","journal-title":"The HTK Book"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2017.09.023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-200"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.eij.2016.04.002"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.04.005"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-1973-7"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2016.7886001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078629"},{"key":"ref65","author":"garofolo","year":"1993","journal-title":"TIMIT Acoust -Phonet Continuous Speech Corpus"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref68","first-page":"4231","article-title":"KSU rich Arabic speech database","volume":"16","author":"alsulaiman","year":"2013","journal-title":"Information"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.11.004"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2014.7073198"},{"key":"ref1","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref93","first-page":"-1009i","article-title":"Whispery speech recognition using adapted articulatory features","volume":"1","author":"jou","year":"2005","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref92","article-title":"Practical selection of SVM supervised parameters with different feature representations for vowel recognition","author":"amami","year":"2015","journal-title":"arXiv 1507 06020"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref90","author":"redmon","year":"2019","journal-title":"Image Classification"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2018-0189"},{"key":"ref99","article-title":"Speech-XLNet: Unsupervised acoustic model pretraining for self-attention networks","author":"song","year":"2019","journal-title":"arXiv 1910 10387"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2012.11.008"},{"key":"ref10","article-title":"Deep learning for generic object detection: A survey","author":"liu","year":"2018","journal-title":"arXiv 1809 02165"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.11.028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s19112577"},{"key":"ref13","article-title":"A framework of transfer learning in object detection for embedded systems","author":"athanasiadis","year":"2018","journal-title":"arXiv 1811 04863"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1749"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref82","article-title":"A breakthrough in speech emotion recognition using deep retinal convolution neural networks","author":"niu","year":"2017","journal-title":"arXiv 1707 09917"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3390\/s19071733"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587597"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2766843"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/MSPEC.1970.5213512"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-38"},{"key":"ref89","article-title":"Comparison and optimization of CNN-based object detectors for fisheye cameras","author":"goodarzi","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref86","author":"tan","year":"2018","journal-title":"Digital Signal Processing Fundamentals and Applications"},{"key":"ref87","author":"redmon","year":"2016","journal-title":"Darknet Open source neural networks in c"},{"key":"ref88","year":"2019","journal-title":"Darknet [Repository]"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09034048.pdf?arnumber=9034048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T01:08:14Z","timestamp":1641949694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9034048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":100,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2980452","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}