{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:49:41Z","timestamp":1767340181279,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/slt.2018.8639642","type":"proceedings-article","created":{"date-parts":[[2019,2,14]],"date-time":"2019-02-14T23:36:34Z","timestamp":1550187394000},"page":"319-324","source":"Crossref","is-referenced-by-count":5,"title":["Data Selection for Improving Naturalness of TTS Voices Trained on Small Found Corpuses"],"prefix":"10.1109","author":[{"given":"F.-Y.","family":"Kuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Aryal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"G.","family":"Degottex","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P.","family":"Lanchantin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I.","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref31","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"year":"0","key":"ref30"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-465"},{"key":"ref11","article-title":"Automatic generation of hyperlinks between audio and transcript","author":"robert-ribes","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref12","article-title":"A recursive algorithm for the forced alignment of very long audio segments","volume":"8","author":"moreno","year":"1998","journal-title":"International Conference on Spoken Language Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0186"},{"key":"ref14","article-title":"An efficient repair procedure for quick transcriptions","author":"venkataraman","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326091"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415062"},{"key":"ref17","first-page":"1626","article-title":"Imperfect transcript driven speech recognition","author":"lecouteux","year":"2006","journal-title":"Proc Inter-speech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2007.4284627"},{"key":"ref19","first-page":"2222","article-title":"Lightly supervised recognition for automatic alignment of large coherent speech recordings","author":"braunschweiler","year":"2010","journal-title":"Proc INTERSPEECH"},{"year":"0","key":"ref28"},{"key":"ref4","article-title":"TUNDRA: a multilingual corpus of found data for TTS research created with light supervision","author":"stan","year":"2013","journal-title":"Proc INTERSPEECH"},{"year":"0","key":"ref27","article-title":"Putonghua Shuiping Ceshi Shishi Gangyao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2081980"},{"key":"ref6","article-title":"Using audio books for training a text-to-speech system","author":"chalamandaris","year":"2014","journal-title":"Proc LREC"},{"year":"0","key":"ref29"},{"key":"ref5","first-page":"101","article-title":"Unsupervised and lightly-supervised learning for rapid construction of TTS systems in multiple languages from found data: evaluation and analysis","author":"watts","year":"2013","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-30"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045237"},{"key":"ref2","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":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2016-162"},{"key":"ref1","article-title":"Reconstructing voices within the multiple-average-voice-model framework","author":"lanchantin","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref20","first-page":"1520","article-title":"Text-to-speech alignment of long recordings using universal phone models","author":"hoffman","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404857"},{"key":"ref21","article-title":"Towards fully automatic annotation of audiobooks for tts","author":"boeffard","year":"2012","journal-title":"International Conference on Language Resources and Evaluation"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2481\/dsj.6.S806"},{"key":"ref23","article-title":"A time delay neural network architecture for efficient modeling of long temporal contexts","author":"peddinti","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref26","article-title":"Improving lightly supervised training for broadcast transcriptions","author":"long","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.01.006"}],"event":{"name":"2018 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2018,12,18]]},"location":"Athens, Greece","end":{"date-parts":[[2018,12,21]]}},"container-title":["2018 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8632666\/8639030\/08639642.pdf?arnumber=8639642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,19]],"date-time":"2019-03-19T01:28:25Z","timestamp":1552958905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8639642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt.2018.8639642","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}