{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T04:11:39Z","timestamp":1748578299006,"version":"3.41.0"},"reference-count":37,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/icme.2015.7177437","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T22:44:22Z","timestamp":1439419462000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Sparse nonlinear representation for voice conversion"],"prefix":"10.1109","author":[{"given":"Toru","family":"Nakashika","sequence":"first","affiliation":[]},{"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[]},{"given":"Yasuo","family":"Ariki","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","first-page":"10","article-title":"Improved learning of gaussian-bernoulli restricted boltzmann machines","author":"cho","year":"2011","journal-title":"ICANN"},{"journal-title":"Unsupervised Learning of Distributions on Binary Vectors Using Two Layer Networks","year":"1994","author":"freund","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315043"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.871582"},{"key":"ref37","first-page":"2421","article-title":"Speech reconstruction from mel-frequency cepstral coefficients using a source-filter model","author":"milner","year":"2002","journal-title":"InterSpeech"},{"key":"ref36","first-page":"3933","article-title":"TANDEM-STRAIGHT: A temporally stable power spectral representation for periodic signals and applications to interference-free spectrum, F0, and aperiodicity estimation","author":"kawahara","year":"2008","journal-title":"ICASSP IEEE"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref34","first-page":"873","article-title":"Sparse deep belief net model for visual area v2","author":"lee","year":"2008","journal-title":"Adv in Neural Info Proc Syst"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","article-title":"Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory","volume":"15","author":"tomoki","year":"2007","journal-title":"IEEE Trans Speech Audio Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041699"},{"key":"ref12","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":"InterSpeech"},{"key":"ref13","first-page":"2254","article-title":"Map-based adaptation for speech conversion using adaptation data selection and nonparallel training","author":"chung-han","year":"2006","journal-title":"InterSpeech"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2269291"},{"key":"ref15","first-page":"3057","article-title":"Exemplar-based unit selection for voice conversion utilizing temporal information","author":"wu","year":"2013","journal-title":"INTER-SPEECH"},{"key":"ref16","first-page":"3062","article-title":"Alleviating the over-smoothing problem in gmm-based voice conversion with discriminative training","author":"hsin-te","year":"2013","journal-title":"InterSpeech"},{"key":"ref17","first-page":"556","article-title":"Algorithms for nonnegative matrix factorization","author":"lee","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424242"},{"key":"ref19","first-page":"71","article-title":"Noise-robust voice conversion based on spectral mapping on sparse space","author":"takashima","year":"2013","journal-title":"SSW8"},{"key":"ref28","first-page":"1339","article-title":"3D object recognition with deep belief nets","author":"nair","year":"2009","journal-title":"NIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940827"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.07.007"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.21437\/Interspeech.2014-295","article-title":"Multimodal exemplar-based voice conversion using lip features in noisy environments","author":"masaka","year":"2014","journal-title":"InterSpeech"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1626431.1626476"},{"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":"InterSpeech"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(92)90012-V"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1984.1162229"},{"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":"InterSpeech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref20","first-page":"3893","article-title":"Voice conversion using artificial neural networks","author":"srinivas","year":"2009","journal-title":"ICASSP IEEE"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625307"},{"key":"ref21","first-page":"3052","article-title":"Joint spectral distribution modeling using restricted boltzmann machines for voice conversion","author":"ling-hui","year":"2013","journal-title":"InterSpeech"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"369","DOI":"10.21437\/Interspeech.2013-102","article-title":"Voice conversion in high-order eigen space using deep belief nets","author":"nakashika","year":"2013","journal-title":"InterSpeech"},{"key":"ref23","first-page":"1345","article-title":"Modeling human motion using binary latent variables","author":"taylor","year":"2006","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1109\/TASL.2011.2109382","article-title":"Acoustic modeling using deep belief networks","volume":"20","author":"abdel-rahman","year":"2012","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref25","first-page":"83","article-title":"Speaker-dependent conditionl restricted boltzmann machine for voice conversion","volume":"113","author":"nakashika","year":"2013","journal-title":"IEICE Technical Report SP2013–88"}],"event":{"name":"2015 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2015,6,29]]},"location":"Turin, Italy","end":{"date-parts":[[2015,7,3]]}},"container-title":["2015 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7160935\/7177375\/07177437.pdf?arnumber=7177437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T23:57:26Z","timestamp":1748563046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7177437"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icme.2015.7177437","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}