{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:37Z","timestamp":1760245057571,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682861","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"6910-6914","source":"Crossref","is-referenced-by-count":8,"title":["Enhancing Hybrid Self-attention Structure with Relative-position-aware Bias for Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Shan","family":"Yang","sequence":"first","affiliation":[]},{"given":"Heng","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Shiying","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2017","journal-title":"arXiv preprint arXiv 1710 07654"},{"key":"ref11","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"arXiv preprint arXiv 1705 03122"},{"key":"ref12","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref13","article-title":"Close to Human Quality TTS with Transformer","author":"li","year":"2018","journal-title":"arXiv preprint arXiv 1809 08895"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1475"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1503"},{"key":"ref17","article-title":"Universal Transformers","author":"dehghani","year":"2018","journal-title":"arXiv preprint arXiv 1807 03819"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref19","article-title":"Wavenet: A generative model for raw audio","author":"den oord","year":"2016","journal-title":"arXiv preprint arXiv 1609 09861"},{"key":"ref4","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-134"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref7","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICLR Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref22","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2017","journal-title":"arXiv preprint arXiv 1712 05884"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent WaveNet vocoder","volume":"2017","author":"tamamori","year":"2017","journal-title":"Proc INTERSPEECH"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682861.pdf?arnumber=8682861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:10:27Z","timestamp":1657854627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682861","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}