{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:34:49Z","timestamp":1730298889827,"version":"3.28.0"},"reference-count":20,"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\/sped53181.2021.9587411","type":"proceedings-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T16:53:34Z","timestamp":1635785614000},"page":"172-176","source":"Crossref","is-referenced-by-count":1,"title":["An analysis of the data efficiency in Tacotron2 speech synthesis system"],"prefix":"10.1109","author":[{"given":"Georgiana","family":"Saracu","sequence":"first","affiliation":[]},{"given":"Adriana","family":"Stan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"schuster","year":"1997","journal-title":"IEEE Transactions on Signal Processing"},{"key":"ref11","article-title":"Attention-based models for speech recognition","volume":"28","author":"chorowski","year":"2015"},{"key":"ref12","article-title":"Parallel tacotron 2: A non-autoregressive neural TTS model with differentiable duration modeling","volume":"abs 2103 14574","author":"elias","year":"2021","journal-title":"CoRR"},{"article-title":"Fastpitch: Parallel text-to-speech with pitch prediction","year":"2021","author":"?a?cucki","key":"ref13"},{"article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","year":"2017","author":"van den oord","key":"ref14"},{"key":"ref15","article-title":"Clarinet: Parallel wave generation in end-to-end text-to-speech","volume":"abs 1807 7281","author":"ping","year":"2018","journal-title":"CoRR"},{"article-title":"Glow: Generative flow with invertible 1×1 convolutions","year":"2018","author":"kingma","key":"ref16"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"The SWARA speech corpus: A large parallel Romanian read speech dataset","author":"stan","year":"2017","journal-title":"Speech Technology and Human-Computer Dialogue (SpeD) 2017 International Conference on"},{"key":"ref19","article-title":"Confidence Intervals for ASR-based TTS Evaluation","author":"taylor","year":"2021","journal-title":"Proceedings of Interspeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053642"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref8","article-title":"Wavenet: A generative model for raw audio","volume":"abs 1609 3499","author":"van den oord","year":"2016","journal-title":"CoRR"},{"key":"ref7","article-title":"Waveglow: A flow-based generative network for speech synthesis","volume":"abs 1811 2","author":"prenger","year":"2018","journal-title":"CoRR"},{"key":"ref2","article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","volume":"abs 2005 5957","author":"valle","year":"2020","journal-title":"CoRR"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"abs 1502 3167","author":"ioffe","year":"2015","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SPED.2019.8906555"}],"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\/09587411.pdf?arnumber=9587411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T12:56:23Z","timestamp":1652187383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9587411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,13]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/sped53181.2021.9587411","relation":{},"subject":[],"published":{"date-parts":[[2021,10,13]]}}}