{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:14:23Z","timestamp":1722575663945},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"JSPS Grant-in-Aid for Scientific Research","award":["25730106"],"award-info":[{"award-number":["25730106"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/taslp.2017.2688585","type":"journal-article","created":{"date-parts":[[2017,3,28]],"date-time":"2017-03-28T20:03:46Z","timestamp":1490731426000},"page":"1107-1116","source":"Crossref","is-referenced-by-count":10,"title":["Sentence Selection Based on Extended Entropy Using Phonetic and Prosodic Contexts for Statistical Parametric Speech Synthesis"],"prefix":"10.1109","volume":"25","author":[{"given":"Takashi","family":"Nose","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusuke","family":"Arao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takao","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Komei","family":"Sugiura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshinori","family":"Shiga","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.825"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0885-2308(86)80009-2"},{"key":"ref33","first-page":"549","article-title":"Structural data-driven prosody model for TTS synthesis","author":"romportl","year":"2006","journal-title":"Proc Speech Prosody"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90011-W"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref30","first-page":"223","article-title":"The CMU Arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc 5th ISCA Speech Synthesis Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758104"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1159\/000028486"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.21437\/Eurospeech.1999-513","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"430","DOI":"10.21437\/Interspeech.2010-177","article-title":"Evaluation of prosodic contextual factors for HMM-based speech synthesis","author":"yokomizo","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743792"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1250\/ast.21.79"},{"key":"ref11","first-page":"2030","article-title":"Corpus design based on the Kullback–Leibler divergence for text-to-speech synthesis application","author":"krul","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref12","first-page":"277","article-title":"Text design for TTS speech corpus building using a modified greedy selection","author":"bozkurt","year":"2003","journal-title":"Proc INTERSPEECH"},{"key":"ref13","first-page":"1381","article-title":"A database design for a TTS synthesis system using lexical diphones","author":"lambert","year":"2004","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"553","DOI":"10.21437\/Eurospeech.1997-207","article-title":"Methods for optimal text selection","author":"van santen","year":"1997","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref15","first-page":"1296","article-title":"Building of a speech corpus optimised for unit selection TTS synthesis","author":"matou\u0161ek","year":"2008","journal-title":"Proc Int Conf on Lang Resources and Evaluation"},{"key":"ref16","first-page":"2102","article-title":"Spanish synthesis corpora","author":"umbert","year":"2006","journal-title":"Proc Int Conf on Lang Resources and Evaluation"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.502"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.11.2484"},{"key":"ref28","first-page":"1","article-title":"ATRECSS: ATR English speech corpus for speech synthesis","author":"ni","year":"2007","journal-title":"Proc Blizzard Challenge Workshop"},{"key":"ref4","first-page":"420","article-title":"A design method of speech corpus for text-to-speech synthesis taking account of prosody","author":"kawai","year":"2000","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref27","first-page":"179","article-title":"XIMERA: A new TTS from ATR based on corpus-based technologies","author":"kawai","year":"2004","journal-title":"Proc 5th ISCA Speech Synth Workshop"},{"key":"ref3","first-page":"2511","article-title":"Combinatorial issues in text-to-speech synthesis","author":"van santen","year":"1997","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref6","first-page":"829","article-title":"Design of an optimal continuous speech database for text-to-speech synthesis considered as a set covering problem","author":"fran\u00e7ois","year":"2001","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref29","article-title":"DARPA TIMIT acoustic phonetic continuous speech corpus CDROM","author":"garofolo","year":"1993"},{"key":"ref5","first-page":"442","article-title":"On building phonetically and prosodically rich speech corpus for text-to-speech synthesis","author":"matou\u0161ek","year":"2006","journal-title":"Proc Comput Intell"},{"key":"ref8","first-page":"211","article-title":"Phonetically balanced word list based on information entropy","author":"shikano","year":"1984","journal-title":"Proc Spring Meeting Acoust Soc Jpn"},{"key":"ref7","first-page":"2047","article-title":"Design of speech corpus for text-to-speech synthesis","author":"matou\u0161ek","year":"2001","journal-title":"Proc Eur Conf Speech Commun Technol"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref9","first-page":"1420","article-title":"The greedy algorithm and its application to the construction of a continuous speech database","author":"fran\u00e7ois","year":"2002","journal-title":"Proc Int Conf on Lang Resources and Evaluation"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9_21"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.09.003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283461"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580298"},{"key":"ref22","first-page":"264","article-title":"How (not) to select your voice corpus: Random selection vs. phonologically balanced","author":"lambert","year":"2007","journal-title":"Proc 6th ISCA Speech Synth Workshop"},{"key":"ref47","first-page":"1043","article-title":"Mel-generalized cepstral analysis—A unified approach to speech spectral estimation","author":"tokuda","year":"1994","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref21","first-page":"3491","article-title":"Entropy-based sentence selection for speech synthesis using phonetic and prosodic contexts","author":"nose","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-1335-6_10"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362403"},{"key":"ref44","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc Int Conf Acoust Speech Signal Process"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2015.1009164"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2013.2283459"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1843","DOI":"10.21437\/Interspeech.2009-536","article-title":"Annotating communicative function and semantic content in dialogue act for construction of consulting dialogue systems","author":"misu","year":"2009","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\/7895265\/07888524.pdf?arnumber=7888524","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T09:09:44Z","timestamp":1719133784000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7888524\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":48,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2688585","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}