{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T15:22:27Z","timestamp":1772205747012,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Plan of China","award":["No.2020AAA0140003"],"award-info":[{"award-number":["No.2020AAA0140003"]}]},{"name":"National Natural Science Foundation of China","award":["No.62101553 No.61901473 No.61831022"],"award-info":[{"award-number":["No.62101553 No.61901473 No.61831022"]}]},{"name":"Key Research Project","award":["No.2019KD0AD01"],"award-info":[{"award-number":["No.2019KD0AD01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,14]]},"DOI":"10.1145\/3552466.3556534","type":"proceedings-article","created":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T12:27:26Z","timestamp":1664627246000},"page":"53-59","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Singing-Tacotron"],"prefix":"10.1145","author":[{"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangyan","family":"Yi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2970241"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Orazio Angelini Alexis Moinet Kayoko Yanagisawa and Thomas Drugman. 2020. Singing Synthesis: with a little help from my attention. arxiv: eess.AS\/1912.05881  Orazio Angelini Alexis Moinet Kayoko Yanagisawa and Thomas Drugman. 2020. Singing Synthesis: with a little help from my attention. arxiv: eess.AS\/1912.05881","DOI":"10.21437\/Interspeech.2020-1399"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Merlijn Blaauw and Jordi Bonada. 2020. Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer. arxiv: cs.SD\/1910.09989  Merlijn Blaauw and Jordi Bonada. 2020. Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer. arxiv: cs.SD\/1910.09989","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"e_1_3_2_2_5_1","volume-title":"August","volume":"15","author":"Blunsom Phil","year":"2004","unstructured":"Phil Blunsom . 2004 . Hidden markov models. Lecture notes , August , Vol. 15 , 18--19 (2004), 48. Phil Blunsom. 2004. Hidden markov models. Lecture notes, August, Vol. 15, 18--19 (2004), 48."},{"key":"e_1_3_2_2_6_1","volume-title":"HiFiSinger: Towards high-fidelity neural singing voice synthesis. arXiv preprint arXiv:2009.01776","author":"Chen Jiawei","year":"2020","unstructured":"Jiawei Chen , Xu Tan , Jian Luan , Tao Qin , and Tie-Yan Liu . 2020. HiFiSinger: Towards high-fidelity neural singing voice synthesis. arXiv preprint arXiv:2009.01776 ( 2020 ). Jiawei Chen, Xu Tan, Jian Luan, Tao Qin, and Tie-Yan Liu. 2020. HiFiSinger: Towards high-fidelity neural singing voice synthesis. arXiv preprint arXiv:2009.01776 (2020)."},{"key":"e_1_3_2_2_7_1","unstructured":"Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based models for speech recognition. In Advances in neural information processing systems. 577--585.  Jan K Chorowski Dzmitry Bahdanau Dmitriy Serdyuk Kyunghyun Cho and Yoshua Bengio. 2015. Attention-based models for speech recognition. In Advances in neural information processing systems. 577--585."},{"key":"e_1_3_2_2_8_1","unstructured":"data baker. Chinese female song 1. https:\/\/test.data-baker.com\/data\/index\/compose.  data baker. Chinese female song 1. https:\/\/test.data-baker.com\/data\/index\/compose."},{"key":"e_1_3_2_2_9_1","unstructured":"Michael Good. 2006. MusicXML in Commercial Applications.  Michael Good. 2006. MusicXML in Commercial Applications."},{"key":"e_1_3_2_2_10_1","volume-title":"Deep learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow , Yoshua Bengio , Aaron Courville , and Yoshua Bengio . 2016. Deep learning . Vol. 1 . MIT press Cambridge . Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep learning. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.5120\/17740-8271"},{"key":"e_1_3_2_2_13_1","volume-title":"Recent Development of the DNN-based Singing Voice Synthesis System - Sinsy. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 1003--1009","author":"Hono Y.","unstructured":"Y. Hono , S. Murata , K. Nakamura , K. Hashimoto , K. Oura , Y. Nankaku , and K. Tokuda . 2018 . Recent Development of the DNN-based Singing Voice Synthesis System - Sinsy. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 1003--1009 . Y. Hono, S. Murata, K. Nakamura, K. Hashimoto, K. Oura, Y. Nankaku, and K. Tokuda. 2018. Recent Development of the DNN-based Singing Voice Synthesis System - Sinsy. In 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). 1003--1009."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"e_1_3_2_2_15_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"e_1_3_2_2_17_1","unstructured":"Juheon Lee Hyeong-Seok Choi Chang-Bin Jeon Junghyun Koo and Kyogu Lee. 2019. Adversarially Trained End-to-end Korean Singing Voice Synthesis System. arxiv: cs.SD\/1908.01919  Juheon Lee Hyeong-Seok Choi Chang-Bin Jeon Junghyun Koo and Kyogu Lee. 2019. Adversarially Trained End-to-end Korean Singing Voice Synthesis System. arxiv: cs.SD\/1908.01919"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"e_1_3_2_2_19_1","volume-title":"Xiaoicesing: A high-quality and integrated singing voice synthesis system. arXiv preprint arXiv:2006.06261","author":"Lu Peiling","year":"2020","unstructured":"Peiling Lu , Jie Wu , Jian Luan , Xu Tan , and Li Zhou . 2020 . Xiaoicesing: A high-quality and integrated singing voice synthesis system. arXiv preprint arXiv:2006.06261 (2020). Peiling Lu, Jie Wu, Jian Luan, Xu Tan, and Li Zhou. 2020. Xiaoicesing: A high-quality and integrated singing voice synthesis system. arXiv preprint arXiv:2006.06261 (2020)."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/1324818"},{"key":"e_1_3_2_2_21_1","volume-title":"Singing voice synthesis based on convolutional neural networks. arXiv preprint arXiv:1904.06868","author":"Nakamura Kazuhiro","year":"2019","unstructured":"Kazuhiro Nakamura , Kei Hashimoto , Keiichiro Oura , Yoshihiko Nankaku , and Keiichi Tokuda . 2019. Singing voice synthesis based on convolutional neural networks. arXiv preprint arXiv:1904.06868 ( 2019 ). Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda. 2019. Singing voice synthesis based on convolutional neural networks. arXiv preprint arXiv:1904.06868 (2019)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Masanari Nishimura Kei Hashimoto Keiichiro Oura Yoshihiko Nankaku and Keiichi Tokuda. 2016. Singing Voice Synthesis Based on Deep Neural Networks.. In Interspeech. 2478--2482.  Masanari Nishimura Kei Hashimoto Keiichiro Oura Yoshihiko Nankaku and Keiichi Tokuda. 2016. Singing Voice Synthesis Based on Deep Neural Networks.. In Interspeech. 2478--2482.","DOI":"10.21437\/Interspeech.2016-1027"},{"key":"e_1_3_2_2_23_1","volume-title":"Seventh ISCA Workshop on Speech Synthesis.","author":"Oura Keiichiro","year":"2010","unstructured":"Keiichiro Oura , Ayami Mase , Tomohiko Yamada , Satoru Muto , Yoshihiko Nankaku , and Keiichi Tokuda . 2010 . Recent development of the HMM-based singing voice synthesis system-Sinsy . In Seventh ISCA Workshop on Speech Synthesis. Keiichiro Oura, Ayami Mase, Tomohiko Yamada, Satoru Muto, Yoshihiko Nankaku, and Keiichi Tokuda. 2010. Recent development of the HMM-based singing voice synthesis system-Sinsy. In Seventh ISCA Workshop on Speech Synthesis."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"e_1_3_2_2_28_1","volume-title":"Forward Attention in Sequence- To-Sequence Acoustic Modeling for Speech Synthesis. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 4789--4793","author":"Zhang J.","unstructured":"J. Zhang , Z. Ling , and L. Dai . 2018 . Forward Attention in Sequence- To-Sequence Acoustic Modeling for Speech Synthesis. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 4789--4793 . J. Zhang, Z. Ling, and L. Dai. 2018. Forward Attention in Sequence- To-Sequence Acoustic Modeling for Speech Synthesis. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 4789--4793."}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552466.3556534","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3552466.3556534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:25Z","timestamp":1750182565000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3552466.3556534"}},"subtitle":["Global Duration Control Attention and Dynamic Filter for End-to-end Singing Voice Synthesis"],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":28,"alternative-id":["10.1145\/3552466.3556534","10.1145\/3552466"],"URL":"https:\/\/doi.org\/10.1145\/3552466.3556534","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}