{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:15:57Z","timestamp":1791303357723,"version":"4.1.0"},"reference-count":217,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Rev. Biomed. Eng."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/rbme.2020.3006860","type":"journal-article","created":{"date-parts":[[2020,7,3]],"date-time":"2020-07-03T20:38:12Z","timestamp":1593808692000},"page":"342-356","source":"Crossref","is-referenced-by-count":164,"title":["Speech Technology for Healthcare: Opportunities, Challenges, and State of the Art"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5662-4777","authenticated-orcid":false,"given":"Siddique","family":"Latif","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9466-2475","authenticated-orcid":false,"given":"Junaid","family":"Qadir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6732-7601","authenticated-orcid":false,"given":"Adnan","family":"Qayyum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-8605","authenticated-orcid":false,"given":"Muhammad","family":"Usama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2489-0234","authenticated-orcid":false,"given":"Shahzad","family":"Younis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","article-title":"Development of isiXhosa text-to-speech modules to support e-services in marginalized rural areas","author":"mhlana","year":"2011"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1044\/2019_PERS-SIG12-2019-0015"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-006-5889-0"},{"key":"ref174","article-title":"Accessed","year":"2020"},{"key":"ref173","article-title":"Accessed","year":"2020"},{"key":"ref176","article-title":"Accessed","year":"2020"},{"key":"ref175","article-title":"Accessed","year":"2020"},{"key":"ref178","article-title":"Accessed","year":"2020"},{"key":"ref177","article-title":"Accessed","year":"2020"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3302509.3313328"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/2388818.2388819"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178826"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3252"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178781"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/AICCSA.2016.7945728"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854048"},{"key":"ref37","first-page":"255","article-title":"Convolutional networks for images, speech, and time series","author":"lecun","year":"0","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref35","article-title":"Feature learning in deep neural networks-studies on speech recognition tasks","author":"yu","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462165"},{"key":"ref181","article-title":"Accessed","year":"2020"},{"key":"ref180","article-title":"Accessed","year":"2020"},{"key":"ref185","article-title":"Accessed","year":"2020"},{"key":"ref184","article-title":"Accessed","year":"2020"},{"key":"ref183","article-title":"Accessed","year":"2020"},{"key":"ref182","article-title":"Accessed","year":"2020"},{"key":"ref189","article-title":"Accessed","year":"2020"},{"key":"ref188","article-title":"Accessed","year":"2020"},{"key":"ref187","article-title":"Accessed","year":"2020"},{"key":"ref186","article-title":"Accessed","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041658"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472791"},{"key":"ref179","article-title":"Accessed","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2014.6900749"},{"key":"ref20","article-title":"The affective reasoner: A process model of emotions in a multi-agent system","author":"elliot","year":"1992"},{"key":"ref22","article-title":"Acoustic feature combination for speech recognition","author":"zolnay","year":"2006"},{"key":"ref21","first-page":"5311","article-title":"What a neural net needs to know about emotion words","volume":"404","author":"cowie","year":"1999","journal-title":"Appl Computat Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2015.7372840"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-31056-5_11"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.dadm.2014.11.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2112351"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2018.2870759"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1250\/ast.28.140"},{"key":"ref156","first-page":"2410","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462431"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2641480"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0199-9_12"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.07.040"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800419"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900070"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaci.2006.08.042"},{"key":"ref58","first-page":"4790","article-title":"Conditional image generation with pixelCNN decoders","author":"oord","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","first-page":"165","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref56","first-page":"1747","article-title":"Pixel recurrent neural networks","volume":"48","author":"oord","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref55","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","author":"kingma","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume":"32","author":"rezende","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1568"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCE.2018.8539336"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/WH.2016.7764555"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CIT\/IUCC\/DASC\/PICOM.2015.209"},{"key":"ref165","article-title":"Text-to-speech based reminder system","author":"li","year":"2001"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-264"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-522"},{"key":"ref160","article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","author":"battenberg","year":"2019"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.18235\/0011233","article-title":"A moving target: Universal access to healthcare services in latin america and the caribbean","author":"savedoff","year":"2009"},{"key":"ref3","year":"2014","journal-title":"Global health workforce shortage to reach 12 9 million in coming decades"},{"key":"ref6","first-page":"322","article-title":"Cloud-based speech technology for assistive technology applications (cloudcast)","author":"cunningham","year":"0","journal-title":"Proc of ATEE Conf"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.3390\/fi9040093","article-title":"How 5G wireless (and concomitant technologies) will revolutionize healthcare","volume":"9","author":"latif","year":"2017","journal-title":"Future Internet"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-14-94"},{"key":"ref159","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00429"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1497185.1497286"},{"key":"ref158","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1625"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref42","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref44","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref43","first-page":"14\ufffd881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-015-0270-2"},{"key":"ref72","article-title":"Medical tele-robotic system with a head worn device","author":"wang","year":"2007"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2020.104178"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-5951-5_11"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1111\/ecc.13033"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-3999(03)00514-2"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.53.4.712"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1093\/clipsy.6.2.204"},{"key":"ref79","article-title":"Cross corpus speech emotion classification—An effective transfer learning technique","author":"latif","year":"2018"},{"key":"ref60","article-title":"Statistics on voice, speech, and language","year":"2016","journal-title":"Nat Inst Deafness Other Commun Disorders"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1163\/9781780522951"},{"key":"ref61","article-title":"Deafness and hearing loss","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.006"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/540409"},{"key":"ref65","first-page":"177","article-title":"Automatic speechreading of impaired speech","author":"potamianos","year":"0","journal-title":"Proc Int Conf Auditory-Visual Speech Process"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3137027"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1363"},{"key":"ref68","article-title":"The role of speech recognition in clinical documentation","author":"wallace","year":"2018","journal-title":"Nuance Communications"},{"key":"ref69","first-page":"53","article-title":"Essential elements of nursing notes and the transition to electronic health records","volume":"24","author":"heinzer","year":"2010","journal-title":"J Healthcare Inform Manage"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2975048"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00009"},{"key":"ref199","article-title":"Deep speech: Scaling up end-to-end speech recognition","author":"hannun","year":"2014"},{"key":"ref193","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref94","first-page":"5067","article-title":"An online sequence-to-sequence model using partial conditioning","author":"jaitly","year":"0","journal-title":"Proc Advances Neural Inform Process Syst"},{"key":"ref190","article-title":"Accessed","year":"2020"},{"key":"ref93","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"0","journal-title":"Proc Int Conf Mach Learn Workshop Represent Learn"},{"key":"ref191","article-title":"Accessed","year":"2020"},{"key":"ref92","article-title":"End-to-end speech recognition: A review for the french language","author":"boyer","year":"2019"},{"key":"ref192","article-title":"Adversarial machine learning and speech emotion recognition: Utilizing generative adversarial networks for robustness","author":"latif","year":"2018"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref98","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053889"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1705"},{"key":"ref97","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","author":"raffel","year":"0","journal-title":"Proc 34th Int Conf Mach Learn -Vol 70"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988267"},{"key":"ref81","article-title":"Deep representation learning in speech processing: Challenges, recent advances, and future trends","author":"latif","year":"2020"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683498"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-644"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2015.03.004"},{"key":"ref89","article-title":"Prospects of voice-enabled healthcare system in the developing nations","author":"oyelami","year":"0","journal-title":"Proc 1st Int Conf Mobile Comput Wireless Commun E-Health M-Health Telemed"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-5225-5270-3.ch011"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2710800"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.pec.2007.03.024"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1001\/archinte.167.14.1503"},{"key":"ref200","article-title":"Did you hear that? Adversarial examples against automatic speech recognition","author":"alzantot","year":"0","journal-title":"Proc Conf Neural Inf Process Syst Mach Deception Workshop"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2230222"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900006"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw4399"},{"key":"ref201","article-title":"Adversarial attacks against automatic speech recognition systems via psychoacoustic hiding","author":"sch\u00f6nherr","year":"2018"},{"key":"ref202","article-title":"Attacking speaker recognition with deep generative models","author":"cai","year":"2018"},{"key":"ref207","doi-asserted-by":"crossref","DOI":"10.17226\/27114","author":"pronovost","year":"2018","journal-title":"Procuring Interoperability Achieving High-quality Connected and Person-Centered Care"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.21037\/mhealth.2017.08.07"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2019.8925513"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2983669"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2215588"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2415"},{"key":"ref212","article-title":"Privacy enhanced multimodal neural representations for emotion recognition","author":"jaiswal","year":"2019"},{"key":"ref213","first-page":"1310","article-title":"Privacy-preserving deep learning","author":"shokri","year":"0","journal-title":"Proc 22nd ACM SIGSAC Conf Comput Commun Secur"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-4666-0134-5"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI.2015.29"},{"key":"ref216","article-title":"Global health care sector outlook","year":"2020","journal-title":"Deloitte"},{"key":"ref217","author":"taylor","year":"2015","journal-title":"Connected health How digital technology is transforming health and social care"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.2174\/1567205014666171120143800"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2680467"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-017-0561-x"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2856238"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2016.7743941"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-150520"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICSEE.2016.7806118"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CCIS.2018.8691393"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2010.2091640"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/3079452.3079492"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1772"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1888"},{"key":"ref135","first-page":"847","article-title":"Investigating voice quality as a speaker-independent indicator of depression and PTSD","author":"scherer","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-019-09631-8"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8903014"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2944380"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-016-0627-x"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/BSN.2019.8771098"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.5772\/intechopen.70106"},{"key":"ref143","first-page":"943","article-title":"The use of telephone speech recordings for assessment and monitoring of cognitive function in elderly people","author":"rapcan","year":"0","journal-title":"Proc 10th Annu Conf Int Speech Commun Assoc"},{"key":"ref2","year":"0","journal-title":"The global burden of chronic"},{"key":"ref144","first-page":"1663","article-title":"Recognition of voice commands by multisource ASR and noise cancellation in a smart home environment","author":"vacher","year":"0","journal-title":"Proc Proc 20th Eur Signal Process Conf"},{"key":"ref1","first-page":"1","article-title":"WHO Expert Consultation on Rabies, 2nd Rep.","year":"2013","journal-title":"World Health Organ Tech Rep Ser"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2772959"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.5072"},{"key":"ref108","first-page":"71","article-title":"Doctors’ handwriting gone digital: An ethical assessment of voice recognition technology in medicine","volume":"29","author":"cheshire","year":"2013","journal-title":"Journal of Medical Ethics"},{"key":"ref107","first-page":"16","article-title":"Speech recognition and keyword spotting for low-resource languages: Babel project research at cued","author":"gales","year":"0","journal-title":"Proc Spoken Language Technologies for Under-resourced Languages"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1780"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054345"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683535"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-016-0374-4"},{"key":"ref112","article-title":"Lessons learned from implementation of voice recognition for documentation in the military electronic health record system","volume":"7","author":"hoyt","year":"2010","journal-title":"Perspectives Health Inform Management\/AHIMA Amer Health Inform Manag Assoc"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-40"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-018-0066-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv152"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy072"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy179"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymeth.2018.07.007"},{"key":"ref15","first-page":"216","article-title":"On preprocessing of speech signals","volume":"5","author":"keerio","year":"2009","journal-title":"Int J Signal Process"},{"key":"ref16","article-title":"Noise suppression and channel equalization preprocessor for speech and speaker recognizers: Method and apparatus","author":"higgins","year":"2001"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.02.011"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1111\/j.1754-9485.2010.02193.x"},{"key":"ref18","article-title":"Text preprocessing for speech synthesis","author":"reichel","year":"2006"},{"key":"ref19","first-page":"2675","article-title":"Politeness and frustration language in child-machine interactions","author":"arunachalam","year":"0","journal-title":"Proc Euro Conf Speech Commun Technol"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx073"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.10.010"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_51"},{"key":"ref116","article-title":"A system for automated extraction of clinical standard codes in spoken medical reports","author":"suendermann-oeft","year":"0","journal-title":"Proc IEEE SLT Workshop"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-015-0048-1"},{"key":"ref120","author":"aronson","year":"2009","journal-title":"Clinical Voice Disorders"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2018.02.003"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1351"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/IWOBI.2017.7985525"}],"container-title":["IEEE Reviews in Biomedical Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4664312\/9333686\/09133298.pdf?arnumber=9133298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T05:28:17Z","timestamp":1723181297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9133298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":217,"URL":"https:\/\/doi.org\/10.1109\/rbme.2020.3006860","relation":{},"ISSN":["1937-3333","1941-1189"],"issn-type":[{"value":"1937-3333","type":"print"},{"value":"1941-1189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}