{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T23:30:13Z","timestamp":1785540613222,"version":"3.56.0"},"reference-count":47,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.23919\/eusipco.2019.8902961","type":"proceedings-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T18:39:38Z","timestamp":1574707178000},"page":"1-5","source":"Crossref","is-referenced-by-count":14,"title":["Effectiveness of Cross-Domain Architectures for Whisper-to-Normal Speech Conversion"],"prefix":"10.23919","author":[{"given":"Mihir","family":"Parmar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Savan","family":"Doshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nirmesh J.","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maitreya","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1565"},{"key":"ref38","article-title":"Computational differences between whispered and non whispered speech","author":"lim","year":"2011","journal-title":"Ph D Thesis Univ of Illinois at Urbana-Champaign"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref32","first-page":"1857","article-title":"Learning to discover cross-domain relations with generative adversarial networks","author":"kim","year":"2017","journal-title":"ICML"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"3364","DOI":"10.21437\/Interspeech.2017-63","article-title":"Voice conversion from unaligned corpora using variational autoencoding Wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"InterSpeech"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282025"},{"key":"ref10","first-page":"1022","article-title":"Reconstruction of continuous voiced speech from whispers","author":"mcloughlin","year":"2013","journal-title":"InterSpeech"},{"key":"ref40","first-page":"1","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"656","DOI":"10.21437\/Interspeech.2009-230","article-title":"Multimodal HMM-basedNAM-to-speech conversion","author":"tran","year":"2009","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.11.005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1487"},{"key":"ref15","article-title":"Non-audible murmur to audible speech conversion","volume":"6","author":"shah","year":"2019","journal-title":"Voice Technologies for Reconstruction and Enhancement"},{"key":"ref16","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"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.1908631"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034676"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.005"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.21437\/Interspeech.2017-970","article-title":"Sequenceto-sequence voice conversion with similarity metric learned using generative adversarial networks","author":"kaneko","year":"2017","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2003.07.003"},{"key":"ref27","first-page":"3642","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.otc.2007.05.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.07.001"},{"key":"ref29","first-page":"5039","article-title":"Time-frequency masking-basedspeech enhancement using generative adversarial network","author":"soni","year":"2018","journal-title":"In ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(98)80058-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S1350-4533(02)00060-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854066"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40136-013-0019-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2737724"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1515\/9781501502415-002","article-title":"Advancements in whispered speech detection for interactive=speech systems","volume":"5","author":"zhang","year":"2018","journal-title":"Signal and Acoustic Modelling for Speech and Communication Disorders"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-22"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953123"},{"key":"ref45","volume":"81","author":"kreyszig","year":"1989","journal-title":"Introductory Functional Analysis With Applications"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.398598"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.03.009"},{"key":"ref21","article-title":"Discrete-Time Speech Signal Processing: Principles and Practice","author":"quatieri","year":"2006","journal-title":"Pearson Education India"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683103"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.21437\/Interspeech.2011-35","article-title":"Improved HNM-basedvocoder for statistical synthesizers","author":"erro","year":"2011","journal-title":"InterSpeech"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1072.001.0001","author":"stevens","year":"2000","journal-title":"Acoustic Mit Press Phonetics"},{"key":"ref44","first-page":"5279","article-title":"High-qualitynonparallel voice conversion based on cycle-consistent adversariel network","author":"fang","year":"2018","journal-title":"ICASSP"},{"key":"ref26","first-page":"2769","article-title":"Non-audible murmur enhancement based on statistical conversion using air-and body-conductive microphones in noisy environments","author":"tajiri","year":"2015","journal-title":"InterSpeech"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1732","DOI":"10.21437\/Interspeech.2010-497","article-title":"Text-independentF0 transformation with non-parallel data for voice conversion","author":"wu","year":"2010","journal-title":"InterSpeech"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1044\/2016_JSLHR-H-15-0435"}],"event":{"name":"2019 27th European Signal Processing Conference (EUSIPCO)","location":"A Coruna, Spain","start":{"date-parts":[[2019,9,2]]},"end":{"date-parts":[[2019,9,6]]}},"container-title":["2019 27th European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8893974\/8902336\/08902961.pdf?arnumber=8902961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,23]],"date-time":"2023-09-23T09:21:28Z","timestamp":1695460888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8902961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":47,"URL":"https:\/\/doi.org\/10.23919\/eusipco.2019.8902961","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}