{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T19:33:15Z","timestamp":1688671995337},"reference-count":35,"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.2013.2294938","type":"journal-article","created":{"date-parts":[[2014,1,31]],"date-time":"2014-01-31T17:45:32Z","timestamp":1391190332000},"page":"323-335","source":"Crossref","is-referenced-by-count":3,"title":["Integrated Expression Prediction and Speech Synthesis From Text"],"prefix":"10.1109","volume":"8","author":[{"given":"Langzhou","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark J. F.","family":"Gales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norbert","family":"Braunschweiler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masami","family":"Akamine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kate","family":"Knill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","author":"young","year":"2006","journal-title":"The HTK Book Version 3 4"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/5.880084"},{"key":"ref31","article-title":"Latent semantic mapping: Principles & applications","author":"bellegarda","year":"2008","journal-title":"Synthesis Lectures on Speech and Audio Processing"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2010-475","article-title":"Prior information for rapid speaker adaptation","author":"breslin","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref35","author":"buchholz","year":"2012","journal-title":"Crowd Sourced Assessment of Speech Synthesis"},{"key":"ref34","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.11.2484"},{"key":"ref12","article-title":"A hidden Markov model-based approach for emotional speech synthesis","author":"yang","year":"2010","journal-title":"Proc 5th ISCA Speech Synth Workshop"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-388","article-title":"A style control technique for speech synthesis using multiple regression HSMM","author":"nose","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367299"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-485","article-title":"Constructing stylistic synthesis databases from audio books","author":"zhao","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref18","article-title":"Automatic building of synthetic voices from large multi-paragraph speech databases","author":"prahallad","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-627","article-title":"Clustering expressive speech styles in audiobooks using glottal source parameters","author":"szekely","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1363686.1364052"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2222","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"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947568"},{"key":"ref6","article-title":"Emotion from text: Machine learning for text-based emotion prediction","author":"ovesdotter alm","year":"2005","journal-title":"Proc Conf HLT-EMNLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0043"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2009.5349598"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876123"},{"key":"ref7","article-title":"Emotional speech synthesis: A review","author":"schr\ufffdder","year":"2001","journal-title":"Proc EUROSPEECH"},{"key":"ref2","article-title":"Wordnet-affect: An affective extension of wordnet","author":"strapparava","year":"2004","journal-title":"Proc LREC"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-560","article-title":"A comparison of voice conversion methods for transforming voice quality in emotional speech synthesis","author":"turk","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/1621474.1621487"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/89.848223"},{"key":"ref22","article-title":"Eigenvoices for HMM-based speech synthesis","author":"shichiri","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2187195"},{"key":"ref24","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":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495689"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CHINSL.2008.ECP.12"},{"key":"ref25","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"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/6763145\/06683056.pdf?arnumber=6683056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T20:09:09Z","timestamp":1648152549000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6683056\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4]]},"references-count":35,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2013.2294938","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,4]]}}}