{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:33:43Z","timestamp":1730230423433,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414402","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"7093-7097","source":"Crossref","is-referenced-by-count":0,"title":["Stable Checkpoint Selection and Evaluation in Sequence to Sequence Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Slava","family":"Shechtman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Haws","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raul","family":"Fernandez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053546"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2914149"},{"key":"ref14","article-title":"DurIAN: Duration informed attention network for multimodal synthesis","volume":"abs 1909 1700","author":"yu","year":"2019","journal-title":"CoRR"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054119"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2123"},{"key":"ref17","article-title":"FastSpeech 2: Fast and high-quality end-to-end Text to Speech","author":"ren","year":"2020","journal-title":"CoRR"},{"key":"ref18","first-page":"275","article-title":"Sequence to Sequence Neural Speech Synthesis with Prosody Modification Capabilities","author":"shechtman","year":"2019","journal-title":"Proc SSW10"},{"key":"ref19","article-title":"Controllable sequence-to-sequence neural TTS with LPC-NET backend for real-time speech synthesis on CPU","author":"shechtman","year":"2020","journal-title":"CoRR"},{"key":"ref4","first-page":"6274","article-title":"Teacherstudent training for robust Tacotron-based TTS","author":"liu","year":"2020","journal-title":"Proc ICASSP"},{"key":"ref3","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"1","author":"bengio","year":"2015","journal-title":"Proc NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-39"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2325"},{"key":"ref8","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume":"abs 1704 784","author":"raffel","year":"2017","journal-title":"CoRR"},{"key":"ref7","article-title":"Non-attentive tacotron: Robust and controllable neural TTS synthesis including unsupervised duration modeling","volume":"abs 2010 4301","author":"shen","year":"2020","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5616"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref22","article-title":"Advancing RNN Transducer technology for speech recognition","author":"saon","year":"2021","journal-title":"ICASSP'16 (Submitted)"},{"key":"ref21","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable Text to Speech","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Sequence transduction with recurrent neural networks","volume":"abs 1211 3711","author":"graves","year":"2012","journal-title":"CoRR"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414402.pdf?arnumber=9414402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:40:55Z","timestamp":1652197255000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414402\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414402","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}