{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T23:28:17Z","timestamp":1729639697993,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/is48319.2020.9199932","type":"proceedings-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T20:50:49Z","timestamp":1600462249000},"page":"437-442","source":"Crossref","is-referenced-by-count":1,"title":["An Evaluation of Postfiltering for Deep Learning Based Speech Synthesis with Limited Data"],"prefix":"10.1109","author":[{"given":"Beata","family":"Loorincz","sequence":"first","affiliation":[]},{"given":"Maria","family":"Nutu","sequence":"additional","affiliation":[]},{"given":"Adriana","family":"Stan","sequence":"additional","affiliation":[]},{"given":"Mircea","family":"Giurgiu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref34","article-title":"Objective intelligibility assessment of text-to-speech systems through utterance verification","author":"ullmann","year":"2015","journal-title":"Idiap Idiap-RR Idiap-RR-06-2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1313"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1460"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472737"},{"key":"ref13","article-title":"Neural Voice Cloning with a Few Samples","volume":"abs 1802 6006","author":"arik","year":"2018","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462373"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SLTU.2018-17"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-172"},{"key":"ref17","article-title":"Voice Imitating Text-to-Speech Neural Networks","volume":"abs 1806 927","author":"lee","year":"2018","journal-title":"CoRR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2461448"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39393-3_28"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2017.7990428"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2007-11508"},{"key":"ref3","article-title":"Parallel WaveNet: Fast High-Fidelity Speech Synthesis","author":"van den oord","year":"2017","journal-title":"Google Tech Rep"},{"key":"ref6","article-title":"Deep Voice 2: Multi-Speaker Neural Text-to-Speech","volume":"abs 1705 8947","author":"arik","year":"2017","journal-title":"CoRR"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2017-1","article-title":"The Blizzard Challenge 2017","author":"king","year":"2017","journal-title":"Proc Blizzard 2017"},{"key":"ref5","article-title":"Deep Voice: Real-time Neural Text-to-Speech","volume":"abs 1702 7825","author":"arik","year":"2017","journal-title":"CoRR"},{"key":"ref8","article-title":"SampleRNN: An Unconditional End-to-End Neural Audio Generation Model","volume":"abs 1612 7837","author":"mehri","year":"2016","journal-title":"CoRR"},{"key":"ref7","article-title":"Deep Voice 3: 2000-Speaker Neural Text-to-Speech","volume":"abs 1710 7654","author":"ping","year":"2017","journal-title":"CoRR"},{"key":"ref2","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den oord","year":"2016","journal-title":"ArXiv"},{"key":"ref9","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"International Conference on Learning Representations Workshops Track"},{"key":"ref1","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","volume":"abs 1712 5884","author":"shen","year":"2017","journal-title":"CoRR"},{"key":"ref20","article-title":"Recurrent neural network postfilters for statistical parametric speech synthesis","volume":"abs 1601 7215","author":"muthukumar","year":"2016","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953090"},{"key":"ref21","first-page":"7030","article-title":"Dnn-based speaker-adaptive postfiltering with limited adaptation data for statistical speech synthesis systems","author":"ztrk","year":"2019","journal-title":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref24","first-page":"4480","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","first-page":"10019","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.06.006"},{"key":"ref25","first-page":"227","article-title":"An HMM-Based Speech Synthesis System Applied To English","author":"tokuda","year":"2002","journal-title":"Proc of SSW6"}],"event":{"name":"2020 IEEE 10th International Conference on Intelligent Systems (IS)","start":{"date-parts":[[2020,8,28]]},"location":"Varna, Bulgaria","end":{"date-parts":[[2020,8,30]]}},"container-title":["2020 IEEE 10th International Conference on Intelligent Systems (IS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9199010\/9199838\/09199932.pdf?arnumber=9199932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T04:43:49Z","timestamp":1723610629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9199932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/is48319.2020.9199932","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}