{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:28:49Z","timestamp":1740101329504,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T00:00:00Z","timestamp":1670716800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100011222","name":"National Laboratory of Pattern Recognition","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011222","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002766","name":"Beijing University of Posts and Telecommunications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002766","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,11]]},"DOI":"10.1109\/iscslp57327.2022.10037822","type":"proceedings-article","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T18:53:24Z","timestamp":1675882404000},"page":"220-224","source":"Crossref","is-referenced-by-count":0,"title":["Rhythm-controllable Attention with High Robustness for Long Sentence Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Dengfeng","family":"Ke","sequence":"first","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yayue","family":"Deng","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukang","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"Xue","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Luo","sequence":"additional","affiliation":[{"name":"Beijing Language and Culture University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Artificial Intelligence,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianqing","family":"Sun","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaen","family":"Liang","sequence":"additional","affiliation":[{"name":"Unisound AI Technology Co., Ltd,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binghuai","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent Technology Co., Ltd,Smart Platform Product Department,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016","journal-title":"arXiv preprint arXiv:1609.03499"},{"key":"ref2","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref3","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2103.00993"},{"key":"ref4","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"ref6","article-title":"Attention-based models for speech recognition","volume":"28","author":"Chorowski","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/ssw.2021-35"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref9","article-title":"Monotonic chunkwise attention","author":"Chiu","year":"2017","journal-title":"arXiv preprint arXiv:1712.05382"},{"key":"ref10","first-page":"2837","article-title":"Online and linear-time attention by enforcing monotonic alignments","volume-title":"International Conference on Machine Learning","author":"Raffel"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.21437\/Interspeech.2019-1972"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.31390\/gradschool_dissertations.4601"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.21437\/Interspeech.2021-1236"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICASSP43922.2022.9746994"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICASSP.2018.8462020"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref17","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref18","article-title":"Emotional end-to-end neural speech synthesizer","author":"Lee","year":"2017","journal-title":"arXiv preprint arXiv:1711.05447"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref20","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"ref21","first-page":"14881","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems","author":"Kumar"},{"key":"ref22","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"}],"event":{"name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2022,12,11]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,12,14]]}},"container-title":["2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10037756\/10037573\/10037822.pdf?arnumber=10037822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:31:03Z","timestamp":1709404263000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10037822\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,11]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/iscslp57327.2022.10037822","relation":{},"subject":[],"published":{"date-parts":[[2022,12,11]]}}}