{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T21:14:11Z","timestamp":1740172451410,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2016,10,1]],"date-time":"2016-10-01T00:00:00Z","timestamp":1475280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000646","name":"JSPS","doi-asserted-by":"publisher","award":["15H02720"],"award-info":[{"award-number":["15H02720"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1109\/taslp.2016.2580298","type":"journal-article","created":{"date-parts":[[2016,6,13]],"date-time":"2016-06-13T21:24:13Z","timestamp":1465853053000},"page":"1694-1704","source":"Crossref","is-referenced-by-count":7,"title":["Efficient Implementation of Global Variance Compensation for Parametric Speech Synthesis"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5403-0019","authenticated-orcid":false,"given":"Takashi","family":"Nose","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"year":"2016","key":"ref32","article-title":"Speech Signal Processing Toolkit (SPTK)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"ref30","first-page":"1240","article-title":"Spectral estimation of speech based on mel-cepstral representation","volume":"j74 a","author":"tokuda","year":"1991","journal-title":"IEICE Trans Fund (Japanese Edition)"},{"key":"ref36","first-page":"173","article-title":"Statistical parametric speech synthesis based on Gaussian process regression","author":"koriyama","year":"2013","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref35","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"article-title":"The HMM-based speech synthesis system (HTS)","year":"2008","author":"tokuda","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853604"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283459"},{"key":"ref12","first-page":"4621","article-title":"Minimum generation error criterion considering global\/local variance for HMM-based speech synthesis","author":"wu","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960511"},{"key":"ref14","first-page":"825","article-title":"Global variance modeling on the log power spectrum of LSPs for HMM-based speech synthesis","author":"ling","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947408"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2165280"},{"key":"ref17","first-page":"889","article-title":"Minimum generation error training for HMM-based speech synthesis","author":"wu","year":"0","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2006.01.002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639196"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref4","article-title":"Recent development of HMM-based expressive speech synthesis and its applications","author":"nose","year":"0","journal-title":"Proc Asia-Pacific Signal Inform Process Assoc Annu Summit Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2182511"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref6","first-page":"2263","article-title":"Mixed excitation for HMM-based speech synthesis","volume":"3","author":"yoshimura","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.09.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref2","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"0","journal-title":"Proc EUROSPEECH"},{"key":"ref9","first-page":"1155","article-title":"Histogram-based spectral equalization for HMM-based speech synthesis using mel-LSP","author":"ohtani","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref1","first-page":"2917","article-title":"Analysis of spectral enhancement using global variance in HMM-based speech synthesis","author":"nose","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.79"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758104"},{"article-title":"Probabilistic acoustic modelling for parametric speech synthesis","year":"2014","author":"shannon","key":"ref24"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2008-7","article-title":"The HTS-2008 system: Yet another evaluation of the speaker-adaptive HMM-based speech synthesis system in the 2008 Blizzard Challenge","author":"yamagishi","year":"2008"},{"key":"ref26","first-page":"94","article-title":"Implementation of computationally efficient real-time voice conversion","author":"toda","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref25","first-page":"1436","article-title":"Ways to implement global variance in statistical speech synthesis.","author":"sil\u00e9n","year":"0","journal-title":"Proc INTERSPEECH"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7524661\/07490416.pdf?arnumber=7490416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T16:00:47Z","timestamp":1718640047000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7490416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10]]},"references-count":36,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2016.2580298","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2016,10]]}}}