{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:29:05Z","timestamp":1778048945261,"version":"3.51.4"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,5]]},"DOI":"10.1109\/icassp.2013.6639220","type":"proceedings-article","created":{"date-parts":[[2013,10,29]],"date-time":"2013-10-29T23:19:46Z","timestamp":1383088786000},"page":"7987-7991","source":"Crossref","is-referenced-by-count":6,"title":["Lightly supervised GMM VAD to use audiobook for speech synthesiser"],"prefix":"10.1109","author":[{"given":"Yoshitaka","family":"Mamiya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Watts","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert A.J.","family":"Clark","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adriana","family":"Stan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","author":"henricus","year":"2008","journal-title":"Segmentation diarization and speech transcription surprise data unraveled"},{"key":"22","article-title":"The CSTR\/EMIME HTS system for blizzard challenge","author":"yamagishi","year":"2010","journal-title":"Proc Blizzard Challenge 2010"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/49.737650"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2003.10.002"},{"key":"15","first-page":"4441","article-title":"A voice activity detection based on the adaptive integration of multiple speech features and a signal decision scheme","author":"fujimoto","year":"2008","journal-title":"Proc ICASSP"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125953"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163642"},{"key":"14","first-page":"41","article-title":"Voice activity detection based on LPCC and spectrum entropy","volume":"50","author":"xiao-jing","year":"2010","journal-title":"Telecommunication Engineering"},{"key":"11","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 Makuhari Japan"},{"key":"12","first-page":"294","article-title":"The HMM-based speech synthesis system (HTS) version 2.0","author":"zen","year":"2007","journal-title":"6th ISCA Workshop on Speech Synthesis Bonn Germany"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266442"},{"key":"3","first-page":"2901","article-title":"Automatic building of synthetic voices from large multi-paragraph speech databases","author":"prahallad","year":"2007","journal-title":"Proc Interspeech Antwerp Belgium"},{"key":"20","article-title":"Evaluation of speech quality measures for the purpose of speaker verification","author":"richiardi","year":"2008","journal-title":"Proc Odyssey 2008 The Speaker and Language Recognition Workshop Stellenbosch South Africa"},{"key":"2","first-page":"2409","article-title":"Clustering expressive speech styles in audiobooks using glottal source parameters","author":"szekely","year":"2011","journal-title":"Proc InterSpeech Florence Italy"},{"key":"1","article-title":"Exploring rich expressive information from audiobook data using cluster adaptive training","author":"chen","year":"2012","journal-title":"Proc Interspeech Portland Oregon"},{"key":"10","first-page":"1821","article-title":"Automatic sentence selection from speech corpora including diverse speech for improved HMM-TTS synthesis quality","author":"braunscheweiler","year":"2011","journal-title":"Proc InterSpeech Florence Italy"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2081980"},{"key":"6","first-page":"1","article-title":"Automatic synchronization of electronic and audio books via TTS alignment and silence filtering","author":"xavier","year":"2011","journal-title":"Proc 2011 IEEE International Conference on Multimedia and Expo Barcelona Spain"},{"key":"5","first-page":"1990","article-title":"Spoken language technologies applied to digital talking books","author":"trancoso","year":"2006","journal-title":"Proc Interspeech Pittsburgh Pennsylvania"},{"key":"4","first-page":"148","article-title":"Handling large audio files in audio books for building synthetic voices","author":"prahallad","year":"2010","journal-title":"Proc The 7th ISCA Tutorial and Research Workshop on Speech Synthesis (SSW7)"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424237"},{"key":"8","first-page":"4593","article-title":"Detecting a targeted voice style in an audiobook using voice quality features","author":"szekely","year":"2012","journal-title":"Proc ICASSP Kyoto Japan"}],"event":{"name":"ICASSP 2013 - 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2013,5,26]]},"end":{"date-parts":[[2013,5,31]]}},"container-title":["2013 IEEE International Conference on Acoustics, Speech and Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6619549\/6637585\/06639220.pdf?arnumber=6639220","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T22:36:09Z","timestamp":1646951769000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6639220\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2013.6639220","relation":{},"subject":[],"published":{"date-parts":[[2013,5]]}}}