{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T05:39:23Z","timestamp":1761975563988},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2016,11,1]],"date-time":"2016-11-01T00:00:00Z","timestamp":1477958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1109\/taslp.2016.2593263","type":"journal-article","created":{"date-parts":[[2016,7,19]],"date-time":"2016-07-19T18:04:28Z","timestamp":1468951468000},"page":"2032-2045","source":"Crossref","is-referenced-by-count":37,"title":["Non-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann Machine"],"prefix":"10.1109","volume":"24","author":[{"given":"Toru","family":"Nakashika","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhiro","family":"Minami","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940842"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/scj.1125"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273596"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_2"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639000"},{"key":"ref37","first-page":"1273","article-title":"VTLN in the MFCC domain: Band-limited versus local interpolation","author":"variani","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.848881"},{"key":"ref35","first-page":"287","article-title":"An attempt to develop a singing synthesizer by collaborative creation","author":"morise","year":"0","journal-title":"Proc Stockholm Music Acoustics Conf"},{"key":"ref34","first-page":"2643","article-title":"Efficient learning of sparse, distributed, convolutional feature representations for object recognition","author":"sohn","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref40","article-title":"Minimizing finite sums with the stochastic average gradient","author":"schmidt","year":"2013"},{"key":"ref11","first-page":"2504","article-title":"Application of matrix variate Gaussian mixture model to statistical voice conversion","author":"saito","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref14","first-page":"71","article-title":"Noise-robust voice conversion based on spectral mapping on sparse space","author":"takashima","year":"0","journal-title":"Proceedings of 8th ISCA Workshop on Speech Synthesis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"ref16","first-page":"3052","article-title":"Joint spectral distribution modeling using restricted Boltzmann machines for voice conversion","author":"chen","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref19","first-page":"369","article-title":"Voice conversion in high-order eigen space using deep belief nets","author":"nakashika","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref28","article-title":"Voice conversion for non-parallel datasets using dynamic kernel partial least squares regression","author":"sil\u00e9n","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940827"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1984.1162229"},{"key":"ref29","article-title":"A framework for cross-lingual voice conversion using artificial neural networks","author":"desai","year":"0","journal-title":"Proc 7th ICON"},{"key":"ref5","first-page":"308","article-title":"Speech generation from hand gestures based on space mapping","author":"kunikoshi","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(92)90012-V"},{"key":"ref2","first-page":"2765","article-title":"Intonation conversion from neutral to expressive speech","author":"veaux","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2379589"},{"key":"ref22","first-page":"2254","article-title":"Map-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.857790"},{"key":"ref24","first-page":"653","article-title":"One-to-many voice conversion based on tensor representation of speaker space","author":"saito","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"2446","article-title":"Eigenvoice conversion based on Gaussian mixture model","author":"toda","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref26","article-title":"Text-independent cross-language voice conversion","author":"s\u00fcndermann","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2225615"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/iel7\/6570655\/7542618\/07516559.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7542618\/07516559.pdf?arnumber=7516559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:26:59Z","timestamp":1642004819000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7516559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11]]},"references-count":40,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2593263","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11]]}}}