{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T18:18:39Z","timestamp":1767896319940,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"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":[],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/spcom50965.2020.9179511","type":"proceedings-article","created":{"date-parts":[[2020,8,28]],"date-time":"2020-08-28T20:20:46Z","timestamp":1598646046000},"page":"1-5","source":"Crossref","is-referenced-by-count":11,"title":["Intelligibility Improvement of Dysarthric Speech using MMSE DiscoGAN"],"prefix":"10.1109","author":[{"given":"Mirali","family":"Purohit","sequence":"first","affiliation":[]},{"given":"Maitreya","family":"Patel","sequence":"additional","affiliation":[]},{"given":"Harshit","family":"Malaviya","sequence":"additional","affiliation":[]},{"given":"Ankur","family":"Patil","sequence":"additional","affiliation":[]},{"given":"Mihir","family":"Parmar","sequence":"additional","affiliation":[]},{"given":"Nirmesh","family":"Shah","sequence":"additional","affiliation":[]},{"given":"Savan","family":"Doshi","sequence":"additional","affiliation":[]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/29.46546"},{"key":"ref32","first-page":"100","article-title":"Speech database development: Design and analysis of the acoustic-phonetic corpus","author":"lamel","year":"1989","journal-title":"Proc DARPA Speech Recogn Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64206-2_16"},{"key":"ref30","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"2011 IEEE Workshop on Automatic Speech Recognition & Understanding"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-172","article-title":"Direct error rate minimization of hidden markov models","author":"keshet","year":"2011","journal-title":"InterSpeech"},{"key":"ref34","first-page":"4521","article-title":"Minimum word classification error training of hmms for automatic speech recognition","author":"yan","year":"2008","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860839"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902961"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.21437\/Eurospeech.1997-363","article-title":"How flexible is the human voice?- a case study of mimicry","author":"eriksson","year":"1997","journal-title":"Fifth European Conference on Speech Communication and Technology"},{"key":"ref13","author":"pathak","year":"2012","journal-title":"Privacy-preserving machine learning for speech processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21849\/cacd.2019.00136"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9924(94)90007-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.3606.1134"},{"key":"ref17","first-page":"5279","article-title":"High-quality nonparallel voice conversion based on cycle-consistent adversariel network","author":"fang","year":"2018","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052966"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDL8034"},{"key":"ref28","article-title":"Dysarthric speech database for universal access research","author":"kim","year":"2008","journal-title":"9th Annual Conference of the International Speech Communication Association"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639230"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref3","first-page":"1","article-title":"Consonant enhancement for articulation disorders based on non-negative matrix factorization","author":"aihara","year":"2012","journal-title":"Proceedings of The 2012 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref29","first-page":"1","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref5","article-title":"Generative adversarial networks for unpaired voice transformation on impaired speech","author":"chen","year":"2018","journal-title":"arXiv preprint arXiv 1810 12656"},{"key":"ref8","first-page":"1","article-title":"Novel MMSE DiscoGAN for cross-domain whisper-to-speech conversion","author":"shah","year":"2018","journal-title":"Machine Learning in Speech and Language Processing (MLSLP) Workshop Google Office"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318526"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2644258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023141"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/SLPAT.2016-8"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref22","article-title":"Improved hnm-based vocoder for statistical synthesizers","author":"erro","year":"2011","journal-title":"Twelfth Annual Conference of the International Speech Communication Association"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref24","article-title":"A convergence theory for deep learning via over-parameterization","author":"allen-zhu","year":"2018","journal-title":"arXiv preprint arXiv 1811 03962"},{"key":"ref23","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref26","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)-Volume 70"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638312"}],"event":{"name":"2020 International Conference on Signal Processing and Communications (SPCOM)","location":"Bangalore, India","start":{"date-parts":[[2020,7,19]]},"end":{"date-parts":[[2020,7,24]]}},"container-title":["2020 International Conference on Signal Processing and Communications (SPCOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9176988\/9179490\/09179511.pdf?arnumber=9179511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T22:51:38Z","timestamp":1668120698000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9179511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/spcom50965.2020.9179511","relation":{},"subject":[],"published":{"date-parts":[[2020,7]]}}}