{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:27:12Z","timestamp":1787012832427,"version":"build-2736575974"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2015,3,1]],"date-time":"2015-03-01T00:00:00Z","timestamp":1425168000000},"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":[[2015,3]]},"DOI":"10.1109\/taslp.2014.2379589","type":"journal-article","created":{"date-parts":[[2014,12,9]],"date-time":"2014-12-09T14:53:22Z","timestamp":1418136802000},"page":"580-587","source":"Crossref","is-referenced-by-count":60,"title":["Voice Conversion Using RNN Pre-Trained by Recurrent Temporal Restricted Boltzmann Machines"],"prefix":"10.1109","volume":"23","author":[{"given":"Toru","family":"Nakashika","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasuo","family":"Ariki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518514"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref33","first-page":"1345","article-title":"Modeling human motion using binary latent variables","author":"taylor","year":"2006","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"3052","article-title":"Joint spectral distribution modeling using restricted Boltzmann machines for voice conversion","author":"chen","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"key":"ref30","article-title":"Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription","author":"boulanger-lewandowski","year":"2012","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref36","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2012","journal-title":"arXiv preprint arXiv 1211 5063"},{"key":"ref35","first-page":"10","article-title":"Improved learning of gaussian-bernoulli restricted Boltzmann machines","author":"cho","year":"2011","journal-title":"Artificial Neural Networks in Machine Learning"},{"key":"ref34","author":"freund","year":"0","journal-title":"Unsupervised Learning of Distributions on Binary Vectors Using Two Layer Networks"},{"key":"ref10","first-page":"2446","article-title":"Eigenvoice conversion based on gaussian mixture model","author":"toda","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref40","first-page":"2421","article-title":"Speech reconstruction from mel-frequency cepstral coefficients using a source-filter model","author":"milner","year":"2002","journal-title":"Proc INTERSPEECH"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"653","DOI":"10.21437\/Interspeech.2011-268","article-title":"One-to-many voice conversion based on tensor representation of speaker space","author":"saito","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.21437\/Interspeech.2010-496","article-title":"Probabilistic integration of joint density model and speaker model for voice conversion","author":"saito","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"},{"key":"ref14","first-page":"629","article-title":"Minimum segmentation error based discriminative training for speech synthesis application","author":"wu","year":"2004","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876778"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2182511"},{"key":"ref18","article-title":"USTC system for blizzard challenge 2006. An improved HMM-based speech synthesis method","author":"ling","year":"2006","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SNPD.2007.133"},{"key":"ref4","first-page":"301","article-title":"High-performance robust speech recognition using stereo training data","author":"deng","year":"2001","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/1626431.1626476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref27","first-page":"1339","article-title":"3-d object recognition with deep belief nets","volume":"22","author":"nair","year":"2009","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"ref29","first-page":"1601","article-title":"The recurrent temporal restricted Boltzmann machine","volume":"19","author":"sutskever","year":"2008","journal-title":"NIPS"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"308","DOI":"10.21437\/Interspeech.2009-102","article-title":"Speech generation from hand gestures based on space mapping","author":"kunikoshi","year":"2009","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","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.21437\/Interspeech.2011-692","article-title":"Intonation conversion from neutral to expressive speech","author":"veaux","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref9","first-page":"2254","article-title":"MAP-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref22","first-page":"369","article-title":"Voice conversion in high-order eigen space using deep belief nets","author":"nakashika","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref21","article-title":"Exemplar-based voice conversion using non-negative spectrogram deconvolution","author":"wu","year":"2013","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6855136"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref41","author":"krizhevsky","year":"2009","journal-title":"?Learning multiple layers of features from tiny images ?"},{"key":"ref23","article-title":"Information processing in dynamical systems: Foundations of harmony theory","volume":"1","author":"smolensky","year":"1986","journal-title":"Parallel Distrib Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7050384\/06980455.pdf?arnumber=6980455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,23]],"date-time":"2022-04-23T23:47:13Z","timestamp":1650757633000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6980455\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,3]]},"references-count":42,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2379589","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,3]]}}}