{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:34:51Z","timestamp":1730298891118,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T00:00:00Z","timestamp":1634083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,13]]},"DOI":"10.1109\/sped53181.2021.9587438","type":"proceedings-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T20:53:34Z","timestamp":1635800014000},"page":"85-90","source":"Crossref","is-referenced-by-count":1,"title":["The MARA corpus: Expressivity in end-to-end TTS systems using synthesised speech data"],"prefix":"10.1109","author":[{"given":"Adriana","family":"Stan","sequence":"first","affiliation":[]},{"given":"Beata","family":"Lorincz","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Nutu","sequence":"additional","affiliation":[]},{"given":"Mircea","family":"Giurgiu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"article-title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","year":"2018","author":"hsu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461888"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2026"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.002"},{"key":"ref16","article-title":"The SWARA Speech Corpus: A Large Parallel Romanian Read Speech Dataset","author":"stan","year":"2017","journal-title":"Proceedings of the 9th Conference on Speech Technology and Human-Computer Dialogue (SpeD)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.06.006"},{"key":"ref18","article-title":"Letter-value plots: Boxplots for large data","volume":"26","author":"heike","year":"2017","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"ref19","first-page":"227","article-title":"An HMM-Based Speech Synthesis System Applied To English","author":"tokuda","year":"2002","journal-title":"Proc of SSW"},{"key":"ref4","first-page":"879","article-title":"A study of speaker adaptation for dnn-based speech synthesis","author":"wu","year":"2015","journal-title":"INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association Dresden Germany September 6–10 2015"},{"key":"ref3","article-title":"Analysis of speaker adaptation algorihms for HMM-based speech synthesis and a constrained SMAPLR adaptation algorithm","author":"yamagishi","year":"2008","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","year":"2018","author":"skerry-ryan","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.03.008"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref1","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"CoRR"},{"key":"ref9","article-title":"Deep encoder-decoder models for unsupervised learning of controllable speech synthesis","volume":"abs 1807 11470","author":"henter","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"7030","DOI":"10.1109\/ICASSP.2019.8683714","article-title":"Dnn-based speakeradaptive postfiltering with limited adaptation data for statistical speech synthesis systems","author":"\u00f6zt\u00fcrk","year":"2019","journal-title":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"}],"event":{"name":"2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","start":{"date-parts":[[2021,10,13]]},"location":"Bucharest, Romania","end":{"date-parts":[[2021,10,15]]}},"container-title":["2021 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9586791\/9587340\/09587438.pdf?arnumber=9587438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:23Z","timestamp":1652201783000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9587438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,13]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/sped53181.2021.9587438","relation":{},"subject":[],"published":{"date-parts":[[2021,10,13]]}}}