{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T05:40:04Z","timestamp":1688967604267},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2014,4,1]],"date-time":"2014-04-01T00:00:00Z","timestamp":1396310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1109\/jstsp.2013.2295058","type":"journal-article","created":{"date-parts":[[2014,1,31]],"date-time":"2014-01-31T17:45:32Z","timestamp":1391190332000},"page":"296-306","source":"Crossref","is-referenced-by-count":2,"title":["Building HMM-TTS Voices on Diverse Data"],"prefix":"10.1109","volume":"8","author":[{"given":"Vincent","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Latorre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kayoko","family":"Yanagisawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norbert","family":"Braunschweiler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Langzhou","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark J. F.","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masami","family":"Akamine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-289","article-title":"Speech factorization for HMM-TTS based on cluster adaptive training","author":"latorre","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref30","first-page":"2250","article-title":"Improving the performance of HMM-Based voice conversion using context clustering decision tree and appropriate regression matrix format","author":"qin","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref10","first-page":"1269","article-title":"Eigenvoices for HMM-based speech synthesis","author":"shichiri","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.9.1406"},{"key":"ref12","first-page":"4234","article-title":"Factor analyzed voice models for HMM-based speech synthesis","author":"kazumi","year":"2012","journal-title":"Proc ICASSP"},{"key":"ref13","first-page":"4469","article-title":"Acoustic modeling with contextual additive structure for HMM-based speech recognition","author":"nankaku","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.03.003"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.21437\/Interspeech.2009-599","article-title":"Context-dependent additive <formula formulatype=\"inline\"> <tex Notation=\"TeX\">$\\log {F}_{0}$<\/tex><\/formula> model for HMM-based speech synthesis","author":"zen","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref16","author":"saino","year":"2008","journal-title":"A clustering technique for factor analyzed voice models"},{"key":"ref17","author":"odell","year":"1995","journal-title":"The use of context in large vocabulary speech recognition"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660231"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"99","DOI":"10.21437\/Eurospeech.1997-52","article-title":"Acoustic modeling based on the MDL criterion for speech recognition","author":"shinoda","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.199"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-764","article-title":"Crowdsourcing preference tests, and how to detect cheating","author":"buchholz","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045237"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.393845"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/89.848223"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/9781118541241.ch7"},{"key":"ref8","year":"0"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-357","article-title":"Combining multiple high quality corpora for improving HMM-TTS","author":"wan","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1250\/ast.33.1"},{"key":"ref9","first-page":"97","article-title":"Adaptation of precision matrix models on large vocabulary continuous speech recognition","author":"sim","year":"2005","journal-title":"Proc ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758104"},{"key":"ref22","author":"young","year":"2003","journal-title":"The HTK Book (for HTK Version 3 2 1)"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-286","article-title":"Exploring rich expressive information from audiobook data using cluster adaptive training","author":"chen","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref24","year":"2010"},{"key":"ref23","first-page":"455","article-title":"Multi-space probability distribution HMM","volume":"e85 d","author":"tokuda","year":"2002","journal-title":"IEICE Trans Inf Syst"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-38","article-title":"Automatic sentence selection from speech corpora including diverse speech for improved HMM-TTS synthesis quality","author":"braunschweiler","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-611","article-title":"Lightly supervised recognition for automatic alignment of large coherent speech recordings","author":"braunschweiler","year":"2010","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/6763145\/06687250.pdf?arnumber=6687250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T04:58:52Z","timestamp":1688965132000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6687250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4]]},"references-count":31,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2013.2295058","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4]]}}}