{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:14:42Z","timestamp":1768436082729,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"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":[[2019,7]]},"DOI":"10.1109\/ijcnn.2019.8852225","type":"proceedings-article","created":{"date-parts":[[2019,9,30]],"date-time":"2019-09-30T23:44:32Z","timestamp":1569887072000},"page":"1-7","source":"Crossref","is-referenced-by-count":3,"title":["An Approach to Cross-Lingual Voice Conversion"],"prefix":"10.1109","author":[{"given":"Sai Sirisha","family":"Rallabandi","sequence":"first","affiliation":[]},{"given":"Suryakanth V","family":"Gangashetty","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"ref33","article-title":"Learning Representations by Back-propagating Errors","author":"rumelhart","year":"1988","journal-title":"Nature A International Journal of Science"},{"key":"ref32","article-title":"Self-Normalizing Neural Networks","volume":"30","author":"klambauer","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"The CMU ARCTIC speech databases","author":"kominek","year":"2004","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref37","article-title":"THCHS-30 : A Free Chinese Speech Corpus","author":"dong wang","year":"2015"},{"key":"ref36","article-title":"The Blizzard Challenge 2010","author":"king","year":"2010","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref10","article-title":"Language independent phoneme mapping for foreign TTS","author":"badino","year":"2004","journal-title":"SSW"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015708"},{"key":"ref12","article-title":"Evaluation of cross-language voice conversion based on GMM and straight","author":"mashimo","year":"2001","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.402284"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318521"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947509"},{"key":"ref16","article-title":"Evaluation of cross-language voice conversion using bilingual and non-bilingual databases","author":"mashimo","year":"2002","journal-title":"Proc Seventh International Conference on Spoken Language Processing"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115676"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472732"},{"key":"ref28","article-title":"Sequence Error (SE) minimization training of neural network for voice conversion","author":"feng-long","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/1467-8721.00140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref3","article-title":"Speech synthesis for mixed-language navigation instructions","author":"raghavi","year":"2017","journal-title":"Proc Inter-speech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2013.6719019"},{"key":"ref29","article-title":"Conditional restricted boltzmann machine for voice conversion","author":"siong","year":"2013","journal-title":"Proc International Conference on Signal and Information Processing (ChinaSIP)"},{"key":"ref5","article-title":"Cross-lingual voice conversion-based polyglot speech synthesizer for Indian languages","author":"ramani","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"A multilingual to polyglot speech synthesizer for indian languages using a voice-converted polyglot speech corpus","author":"vijayalakshmi","year":"2017","journal-title":"CSSP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-015-0118-1"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.05.003"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref22","article-title":"Autoencoders, minimum description length and helmholtz free energy","author":"hinton","year":"1994","journal-title":"Proc Advances in Neural Information Processing Systems 6"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-30"},{"key":"ref26","article-title":"Spectral Mapping using Artificial Neural Networks for Voice Conversion","author":"srinivas","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960478"}],"event":{"name":"2019 International Joint Conference on Neural Networks (IJCNN)","location":"Budapest, Hungary","start":{"date-parts":[[2019,7,14]]},"end":{"date-parts":[[2019,7,19]]}},"container-title":["2019 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8840768\/8851681\/08852225.pdf?arnumber=8852225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:54:04Z","timestamp":1658080444000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8852225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2019.8852225","relation":{},"subject":[],"published":{"date-parts":[[2019,7]]}}}