{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:11:57Z","timestamp":1766067117770},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054106","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"6194-6198","source":"Crossref","is-referenced-by-count":54,"title":["Location-Relative Attention Mechanisms for Robust Long-Form Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Eric","family":"Battenberg","sequence":"first","affiliation":[]},{"given":"R.J.","family":"Skerry-Ryan","sequence":"additional","affiliation":[]},{"given":"Soroosh","family":"Mariooryad","sequence":"additional","affiliation":[]},{"given":"Daisy","family":"Stanton","sequence":"additional","affiliation":[]},{"given":"David","family":"Kao","sequence":"additional","affiliation":[]},{"given":"Matt","family":"Shannon","sequence":"additional","affiliation":[]},{"given":"Tom","family":"Bagby","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"4693","article-title":"Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron","author":"skerry-ryan","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682880"},{"key":"ref12","article-title":"Effective Use of Variational Embedding Capacity in Expressive End-to-End Speech Synthesis","author":"battenberg","year":"2019","journal-title":"ArXiv org"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref14","first-page":"2410","article-title":"Efficient Neural Audio Synthesis","author":"kalchbrenner","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"article-title":"The LJ Speech Dataset","year":"2017","author":"ito","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref3","first-page":"4006","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"0","journal-title":"Proc Interspeech 2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462020"},{"key":"ref8","first-page":"577","article-title":"Attention-based Models for Speech Recognition","author":"chorowski","year":"2015","journal-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1"},{"key":"ref7","article-title":"Maximizing Mutual Information for Tacotron","author":"liu","year":"2019","journal-title":"ArXiv org"},{"key":"ref2","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref1","article-title":"Generating Sequences With Recurrent Neural Networks","author":"graves","year":"2013","journal-title":"ArXiv org"},{"key":"ref9","first-page":"2837","article-title":"Online and Linear-time Attention by Enforcing Monotonic Alignments","author":"raffel","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning-Volume 70"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054106.pdf?arnumber=9054106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:16:36Z","timestamp":1656360996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054106\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054106","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}