{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:09:52Z","timestamp":1729634992564,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1109\/iscslp.2014.6936599","type":"proceedings-article","created":{"date-parts":[[2014,11,1]],"date-time":"2014-11-01T03:05:21Z","timestamp":1414811121000},"page":"197-200","source":"Crossref","is-referenced-by-count":6,"title":["Pitch transformation in neural network based voice conversion"],"prefix":"10.1109","author":[{"given":"Feng-Long","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank K.","family":"Soong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haifeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","first-page":"26","article-title":"Line spectral pairs based voice conversion using radial basis function","volume":"4","author":"nirmal","year":"2013","journal-title":"Signal & Image Processing : An International Journal"},{"key":"22","first-page":"333","article-title":"Spectral conversion based on statistical models including time-sequence matching","author":"nankaku","year":"2007","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"17","article-title":"The CMU ARCTIC databases for speech synthesis","author":"kominek","year":"2003","journal-title":"Tech Rep CMU-LTI-03-177"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947371"},{"key":"18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-765","article-title":"Growing a spoken language interface on amazon mechanical turk","author":"mcgraw","year":"2011","journal-title":"Proc of Interspeech"},{"key":"24","article-title":"Sequence Error (SE) minimization training of neural network for voice conversion","author":"xie","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"15","first-page":"3053","article-title":"Joint spectral distribution modeling using restricted boltzmann machines for voice conversion","author":"chen","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.1993.318181"},{"key":"13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-598","article-title":"A hierarchical F0 modelling method for HMM-based speech synthesis","author":"lei","year":"2010","journal-title":"Proc of Interspeech"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/FSKD.2007.347"},{"key":"11","first-page":"1961","article-title":"F0 transformation within the voice convesrion framework","author":"hanzlicek","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/CHINSL.2008.ECP.44"},{"key":"21","doi-asserted-by":"crossref","first-page":"1072","DOI":"10.21437\/Interspeech.2008-331","article-title":"Simultaneous conversion of duration and spectrum based on statistical models including time-sequence matching","author":"yutani","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(94)00058-I"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-38847-7_13"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"10","first-page":"556","article-title":"Duration modelling in voice conversion using artificial neural networks","author":"srikanth","year":"2012","journal-title":"Proc IWSSIP"},{"key":"7","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.21437\/Interspeech.2008-335","article-title":"Incorporating durational modification in voice transformation","author":"toth","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"6","article-title":"Estimating phrase curves in the general superpositional intonation model","author":"van santen","year":"2004","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"5","first-page":"78","article-title":"Continuous wavelet transform for analysis of speech prosody","author":"vainio","year":"2013","journal-title":"TRASP"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047683"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225951"}],"event":{"name":"2014 9th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2014,9,12]]},"location":"Singapore, Singapore","end":{"date-parts":[[2014,9,14]]}},"container-title":["The 9th International Symposium on Chinese Spoken Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6924027\/6936571\/06936599.pdf?arnumber=6936599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,20]],"date-time":"2022-04-20T21:50:52Z","timestamp":1650491452000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6936599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,9]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2014.6936599","relation":{},"subject":[],"published":{"date-parts":[[2014,9]]}}}