{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T07:53:30Z","timestamp":1760255610421,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9052966","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7764-7768","source":"Crossref","is-referenced-by-count":11,"title":["Mspec-Net : Multi-Domain Speech Conversion Network"],"prefix":"10.1109","author":[{"given":"Harshit","family":"Malaviya","sequence":"first","affiliation":[]},{"given":"Jui","family":"Shah","sequence":"additional","affiliation":[]},{"given":"Maitreya","family":"Patel","sequence":"additional","affiliation":[]},{"given":"Jalansh","family":"Munshi","sequence":"additional","affiliation":[]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-16"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854066"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S1350-4533(02)00060-7"},{"key":"ref13","first-page":"1022","article-title":"Reconstruction of continuous voiced speech from whispers","author":"mcloughlin","year":"2013","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1565"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.140"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00573"},{"key":"ref19","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref4","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 De Gruyter"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s40136-013-0019-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.11.005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2205241"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-583","article-title":"Improving body transmitted unvoiced speech with statistical voice conversion","author":"nakagiri","year":"2006","journal-title":"InterSpeech"},{"key":"ref7","first-page":"1957","article-title":"NAM-to-speech conversion with Gaussian mixture models","author":"toda","year":"2005","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(98)80058-1"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2003.07.003"},{"journal-title":"European Signal Processing Conference (EUSIPCO)","year":"2019","author":"parmar","key":"ref9"},{"year":"0","key":"ref20","article-title":"Publicly available: The CSTR NAM TIMIT Plus Corpus"},{"key":"ref22","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"San Jose CA USA"},{"key":"ref21","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":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref23","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"},{"year":"1994","key":"ref25","article-title":"A method for subjective performance assessment of the quality of speech voice output devices"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09052966.pdf?arnumber=9052966","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T15:28:53Z","timestamp":1696001333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052966\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9052966","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}