{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:53:38Z","timestamp":1753602818215},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,24]],"date-time":"2021-01-24T00:00:00Z","timestamp":1611446400000},"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":[[2021,1,24]]},"DOI":"10.1109\/iscslp49672.2021.9362072","type":"proceedings-article","created":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T23:37:05Z","timestamp":1614641825000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["MoEVC: A Mixture of Experts Voice Conversion System With Sparse Gating Mechanism for Online Computation Acceleration"],"prefix":"10.1109","author":[{"given":"Yu-Tao","family":"Chang","sequence":"first","affiliation":[]},{"given":"Yuan-Hong","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Yu-Huai","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Syu-Siang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Tai-Shih","family":"Chi","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"article-title":"Learning factored representations in a deep mixture of experts","year":"2013","author":"eigen","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"year":"0","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref36","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"qian","year":"0","journal-title":"Proc ICML 2019"},{"key":"ref35","article-title":"Ways to implement global variance in statistical speech synthesis","author":"sil\u00e9n","year":"0","journal-title":"Proc Interspeech 2012"},{"key":"ref34","article-title":"Melcepstral distance measure for objective speech quality assessment","author":"kubichek","year":"0","journal-title":"Proc PACRIM 1993"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref40","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"0","journal-title":"Proc ICML 2015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-567"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref15","article-title":"Voice conversion from unaligned corpora using variational au-toencoding wasserstein generative adversarial networks","author":"hsu","year":"0","journal-title":"Proc Interspeech 2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref17","article-title":"Atts2svc: Sequence-to-sequence voice conversion with attention and con-text preservation mechanisms","author":"tanaka","year":"0","journal-title":"Proc ICASSP 2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659543"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_19"},{"article-title":"Unsupervised speech decomposition via triple information bot-tleneck","year":"2020","author":"qian","key":"ref4"},{"article-title":"Pruning filters for efficient convnets","year":"2016","author":"li","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054596"},{"article-title":"Acvaevc: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder","year":"2018","author":"kameoka","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2286917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2875195"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1357"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1774"},{"article-title":"Precision scaling of neural networks for efficient audio processing","year":"2017","author":"ko","key":"ref22"},{"key":"ref21","article-title":"A study on speech enhancement using exponent-only floating point quantized neural network (eofpqnn)","author":"hsu","year":"0","journal-title":"Proc SLT 2018"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"article-title":"Deep mixture of experts via shallow embedding","year":"2018","author":"wang","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"}],"event":{"name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2021,1,24]]},"location":"Hong Kong","end":{"date-parts":[[2021,1,27]]}},"container-title":["2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9362048\/9362049\/09362072.pdf?arnumber=9362072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:57Z","timestamp":1652197317000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9362072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,24]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/iscslp49672.2021.9362072","relation":{},"subject":[],"published":{"date-parts":[[2021,1,24]]}}}