{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T18:25:11Z","timestamp":1788459911801,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key R&D Program of China","award":["2018AAA0100603"],"award-info":[{"award-number":["2018AAA0100603"]}]},{"name":"Microsoft Research Asia"},{"name":"the Fundamental Research Funds for the Central Universities","award":["2020QNA5024"],"award-info":[{"award-number":["2020QNA5024"]}]},{"name":"Zhejiang Natural Science Foundation","award":["LR19F020006"],"award-info":[{"award-number":["LR19F020006"]}]},{"name":"National Natural Science Foundation of China","award":["61836002,U1611461,61751209"],"award-info":[{"award-number":["61836002,U1611461,61751209"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,8,23]]},"DOI":"10.1145\/3394486.3403249","type":"proceedings-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T23:03:59Z","timestamp":1597964639000},"page":"1979-1989","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["DeepSinger: Singing Voice Synthesis with Data Mined From the Web"],"prefix":"10.1145","author":[{"given":"Yi","family":"Ren","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Luan","sequence":"additional","affiliation":[{"name":"Microsoft STC Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.3390\/app7121313"},{"key":"e_1_3_2_1_2_1","volume-title":"Glot international","volume":"5","author":"Paul","year":"2002","unstructured":"Paul Boersma et al. 2002. Praat, a system for doing phonetics by computer . Glot international , Vol. 5 ( 2002 ). Paul Boersma et al. 2002. Praat, a system for doing phonetics by computer. Glot international, Vol. 5 (2002)."},{"key":"e_1_3_2_1_3_1","unstructured":"Jamie Callan Mark Hoy Changkuk Yoo and Le Zhao. 2009. Clueweb09 data set.  Jamie Callan Mark Hoy Changkuk Yoo and Le Zhao. 2009. Clueweb09 data set."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"e_1_3_2_1_5_1","volume-title":"WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN. arXiv preprint arXiv:1903.10729","author":"Chandna Pritish","year":"2019","unstructured":"Pritish Chandna , Merlijn Blaauw , Jordi Bonada , and Emilia Gomez . 2019. WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN. arXiv preprint arXiv:1903.10729 ( 2019 ). Pritish Chandna, Merlijn Blaauw, Jordi Bonada, and Emilia Gomez. 2019. WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN. arXiv preprint arXiv:1903.10729 (2019)."},{"key":"e_1_3_2_1_6_1","first-page":"1998","article-title":"Alignment of lyrics with accompanied singing audio based on acoustic-phonetic vowel likelihood modeling","volume":"24","author":"Chien Yu-Ren","year":"2016","unstructured":"Yu-Ren Chien , Hsin-Min Wang , Shyh-Kang Jeng , Yu-Ren Chien , Hsin-Min Wang , and Shyh-Kang Jeng . 2016 . Alignment of lyrics with accompanied singing audio based on acoustic-phonetic vowel likelihood modeling . TASLP , Vol. 24 , 11 (2016), 1998 -- 2008 . Yu-Ren Chien, Hsin-Min Wang, Shyh-Kang Jeng, Yu-Ren Chien, Hsin-Min Wang, and Shyh-Kang Jeng. 2016. Alignment of lyrics with accompanied singing audio based on acoustic-phonetic vowel likelihood modeling. TASLP, Vol. 24, 11 (2016), 1998--2008.","journal-title":"TASLP"},{"key":"e_1_3_2_1_7_1","volume-title":"Alec Radford, and Ilya Sutskever.","author":"Dhariwal Prafulla","year":"2020","unstructured":"Prafulla Dhariwal , Heewoo Jun , Christine Payne , Jong Wook Kim , Alec Radford, and Ilya Sutskever. 2020 . Jukebox : A generative model for music. arXiv preprint arXiv:2005.00341 (2020). Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, and Ilya Sutskever. 2020. Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341 (2020)."},{"key":"e_1_3_2_1_8_1","unstructured":"Zhiyong Zhang Dong Wang Xuewei Zhang. 2015. THCHS-30 : A Free Chinese Speech Corpus. http:\/\/arxiv.org\/abs\/1512.01882  Zhiyong Zhang Dong Wang Xuewei Zhang. 2015. THCHS-30 : A Free Chinese Speech Corpus. http:\/\/arxiv.org\/abs\/1512.01882"},{"key":"e_1_3_2_1_9_1","unstructured":"Georgi Dzhambazov et al. 2017. Knowledge-based probabilistic modeling for tracking lyrics in music audio signals. Ph.D. Dissertation. Universitat Pompeu Fabra.  Georgi Dzhambazov et al. 2017. Knowledge-based probabilistic modeling for tracking lyrics in music audio signals. Ph.D. Dissertation. Universitat Pompeu Fabra."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159577"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"e_1_3_2_1_12_1","unstructured":"Chitralekha Gupta Rong Tong Haizhou Li and Ye Wang. 2018. Semi-supervised Lyrics and Solo-singing Alignment.. In ISMIR. 600--607.  Chitralekha Gupta Rong Tong Haizhou Li and Ye Wang. 2018. Semi-supervised Lyrics and Solo-singing Alignment.. In ISMIR. 600--607."},{"key":"e_1_3_2_1_13_1","volume-title":"Acoustic Modeling for Automatic Lyrics-to-Audio Alignment. arXiv preprint arXiv:1906.10369","author":"Gupta Chitralekha","year":"2019","unstructured":"Chitralekha Gupta , Emre Yilmaz , and Haizhou Li. 2019. Acoustic Modeling for Automatic Lyrics-to-Audio Alignment. arXiv preprint arXiv:1906.10369 ( 2019 ). Chitralekha Gupta, Emre Yilmaz, and Haizhou Li. 2019. Acoustic Modeling for Automatic Lyrics-to-Audio Alignment. arXiv preprint arXiv:1906.10369 (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Proc. International Society for Music Information Retrieval Conference .","author":"Hennequin Romain","year":"2019","unstructured":"Romain Hennequin , Anis Khlif , Felix Voituret , and Manuel Moussalam . 2019 . Spleeter: A fast and state-of-the art music source separation tool with pre-trained models . In Proc. International Society for Music Information Retrieval Conference . Romain Hennequin, Anis Khlif, Felix Voituret, and Manuel Moussalam. 2019. Spleeter: A fast and state-of-the art music source separation tool with pre-trained models. In Proc. International Society for Music Information Retrieval Conference ."},{"key":"e_1_3_2_1_15_1","volume-title":"Singing Voice Synthesis Based on Generative Adversarial Networks. In ICASSP","author":"Hono Yukiya","year":"2019","unstructured":"Yukiya Hono , Kei Hashimoto , Keiichiro Oura , Yoshihiko Nankaku , and Keiichi Tokuda . 2019 . Singing Voice Synthesis Based on Generative Adversarial Networks. In ICASSP 2019. IEEE, 6955--6959. Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda. 2019. Singing Voice Synthesis Based on Generative Adversarial Networks. In ICASSP 2019. IEEE, 6955--6959."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"e_1_3_2_1_17_1","volume-title":"RTRL, EKF and the\" echo state network\" approach.","author":"Jaeger Herbert","unstructured":"Herbert Jaeger . 2002. Tutorial on training recurrent neural networks, covering BPPT , RTRL, EKF and the\" echo state network\" approach. Vol. 5 . GMD-Forschungszentrum Informationstechnik Bonn . Herbert Jaeger. 2002. Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the\" echo state network\" approach. Vol. 5. GMD-Forschungszentrum Informationstechnik Bonn."},{"key":"e_1_3_2_1_18_1","volume-title":"Efficient neural audio synthesis. arXiv preprint arXiv:1802.08435","author":"Kalchbrenner Nal","year":"2018","unstructured":"Nal Kalchbrenner , Erich Elsen , Karen Simonyan , Seb Noury , Norman Casagrande , Edward Lockhart , Florian Stimberg , Aaron van den Oord , Sander Dieleman , and Koray Kavukcuoglu . 2018. Efficient neural audio synthesis. arXiv preprint arXiv:1802.08435 ( 2018 ). Nal Kalchbrenner, Erich Elsen, Karen Simonyan, Seb Noury, Norman Casagrande, Edward Lockhart, Florian Stimberg, Aaron van den Oord, Sander Dieleman, and Koray Kavukcuoglu. 2018. Efficient neural audio synthesis. arXiv preprint arXiv:1802.08435 (2018)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"e_1_3_2_1_20_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_1_21_1","volume-title":"Adversarially Trained End-to-end Korean Singing Voice Synthesis System. arXiv preprint arXiv:1908.01919","author":"Lee Juheon","year":"2019","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 preprint arXiv:1908.01919 ( 2019 ). 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 preprint arXiv:1908.01919 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"EMPHASIS: An emotional phoneme-based acoustic model for speech synthesis system. arXiv preprint arXiv:1806.09276","author":"Li Hao","year":"2018","unstructured":"Hao Li , Yongguo Kang , and Zhenyu Wang . 2018 . EMPHASIS: An emotional phoneme-based acoustic model for speech synthesis system. arXiv preprint arXiv:1806.09276 (2018). Hao Li, Yongguo Kang, and Zhenyu Wang. 2018. EMPHASIS: An emotional phoneme-based acoustic model for speech synthesis system. arXiv preprint arXiv:1806.09276 (2018)."},{"key":"e_1_3_2_1_23_1","volume-title":"Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862","author":"Li Wen","year":"2017","unstructured":"Wen Li , Limin Wang , Wei Li , Eirikur Agustsson , and Luc Van Gool . 2017. Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862 ( 2017 ). Wen Li, Limin Wang, Wei Li, Eirikur Agustsson, and Luc Van Gool. 2017. Webvision database: Visual learning and understanding from web data. arXiv preprint arXiv:1708.02862 (2017)."},{"key":"e_1_3_2_1_24_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_1_25_1","doi-asserted-by":"crossref","unstructured":"Michael McAuliffe Michaela Socolof Sarah Mihuc Michael Wagner and Morgan Sonderegger. 2017. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi. In Interspeech. 498--502.  Michael McAuliffe Michaela Socolof Sarah Mihuc Michael Wagner and Morgan Sonderegger. 2017. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi. In Interspeech. 498--502.","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 11th Int. Conference on Digital Audio Effects (DAFx-08)","author":"Mesaros Annamaria","year":"2008","unstructured":"Annamaria Mesaros and Tuomas Virtanen . 2008 . Automatic alignment of music audio and lyrics . In Proceedings of the 11th Int. Conference on Digital Audio Effects (DAFx-08) . Annamaria Mesaros and Tuomas Virtanen. 2008. Automatic alignment of music audio and lyrics. In Proceedings of the 11th Int. Conference on Digital Audio Effects (DAFx-08) ."},{"key":"e_1_3_2_1_27_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_1_28_1","unstructured":"Thi Hao Nguyen. 2018. A Study on Correlates of Acoustic Features to Emotional Singing Voice Synthesis. (2018).  Thi Hao Nguyen. 2018. A Study on Correlates of Acoustic Features to Emotional Singing Voice Synthesis. (2018)."},{"key":"e_1_3_2_1_29_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_1_30_1","volume-title":"Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499","author":"van den Oord Aaron","year":"2016","unstructured":"Aaron van den Oord , Sander Dieleman , Heiga Zen , Karen Simonyan , Oriol Vinyals , Alex Graves , Nal Kalchbrenner , Andrew Senior , and Koray Kavukcuoglu . 2016 . Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016). Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, Oriol Vinyals, Alex Graves, Nal Kalchbrenner, Andrew Senior, and Koray Kavukcuoglu. 2016. Wavenet: A generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)."},{"key":"e_1_3_2_1_31_1","unstructured":"Wei Ping Kainan Peng and Jitong Chen. 2019. ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech. In ICLR .  Wei Ping Kainan Peng and Jitong Chen. 2019. ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech. In ICLR ."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9123-y"},{"key":"e_1_3_2_1_33_1","volume-title":"FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech. arXiv preprint arXiv:2006.04558","author":"Ren Yi","year":"2020","unstructured":"Yi Ren , Chenxu Hu , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , and Tie-Yan Liu . 2020. FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech. arXiv preprint arXiv:2006.04558 ( 2020 ). Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2020. FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech. arXiv preprint arXiv:2006.04558 (2020)."},{"key":"e_1_3_2_1_34_1","volume-title":"Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3171--3180.","author":"Ren Yi","year":"2019","unstructured":"Yi Ren , Yangjun Ruan , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , and Tie-Yan Liu . 2019 . Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3171--3180. Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. Fastspeech: Fast, robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3171--3180."},{"key":"e_1_3_2_1_35_1","volume-title":"Automatic Lyrics-to-audio Alignment on Polyphonic Music Using Singing-adapted Acoustic Models. In ICASSP","author":"Sharma Bidisha","year":"2019","unstructured":"Bidisha Sharma , Chitralekha Gupta , Haizhou Li , and Ye Wang . 2019 . Automatic Lyrics-to-audio Alignment on Polyphonic Music Using Singing-adapted Acoustic Models. In ICASSP 2019. IEEE, 396--400. Bidisha Sharma, Chitralekha Gupta, Haizhou Li, and Ye Wang. 2019. Automatic Lyrics-to-audio Alignment on Polyphonic Music Using Singing-adapted Acoustic Models. In ICASSP 2019. IEEE, 396--400."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2424572"},{"key":"e_1_3_2_1_39_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_40_1","volume-title":"Merlin: An Open Source Neural Network Speech Synthesis System.. In SSW. 202--207.","author":"Wu Zhizheng","year":"2016","unstructured":"Zhizheng Wu , Oliver Watts , and Simon King . 2016 . Merlin: An Open Source Neural Network Speech Synthesis System.. In SSW. 202--207. Zhizheng Wu, Oliver Watts, and Simon King. 2016. Merlin: An Open Source Neural Network Speech Synthesis System.. In SSW. 202--207."},{"key":"e_1_3_2_1_41_1","volume-title":"Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5754--5764.","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang , Zihang Dai , Yiming Yang , Jaime Carbonell , Russ R Salakhutdinov , and Quoc V Le . 2019 . Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5754--5764. Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in neural information processing systems. 5754--5764."},{"key":"e_1_3_2_1_42_1","unstructured":"Yuan-Hao Yi Yang Ai Zhen-Hua Ling and Li-Rong Dai. 2019. Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling. (2019).  Yuan-Hao Yi Yang Ai Zhen-Hua Ling and Li-Rong Dai. 2019. Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling. (2019)."},{"key":"e_1_3_2_1_43_1","volume-title":"LibriTTS: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882","author":"Zen Heiga","year":"2019","unstructured":"Heiga Zen , Viet Dang , Rob Clark , Yu Zhang , Ron J Weiss , Ye Jia , Zhifeng Chen , and Yonghui Wu. 2019. LibriTTS: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 ( 2019 ). Heiga Zen, Viet Dang, Rob Clark, Yu Zhang, Ron J Weiss, Ye Jia, Zhifeng Chen, and Yonghui Wu. 2019. LibriTTS: A corpus derived from librispeech for text-to-speech. arXiv preprint arXiv:1904.02882 (2019)."},{"key":"e_1_3_2_1_44_1","volume-title":"Learning Singing From Speech. arXiv preprint arXiv:1912.10128","author":"Zhang Liqiang","year":"2019","unstructured":"Liqiang Zhang , Chengzhu Yu , Heng Lu , Chao Weng , Yusong Wu , Xiang Xie , Zijin Li , and Dong Yu. 2019. Learning Singing From Speech. arXiv preprint arXiv:1912.10128 ( 2019 ). Liqiang Zhang, Chengzhu Yu, Heng Lu, Chao Weng, Yusong Wu, Xiang Xie, Zijin Li, and Dong Yu. 2019. Learning Singing From Speech. arXiv preprint arXiv:1912.10128 (2019)."}],"event":{"name":"KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event CA USA","acronym":"KDD '20","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403249","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394486.3403249","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:47Z","timestamp":1750197707000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403249"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":44,"alternative-id":["10.1145\/3394486.3403249","10.1145\/3394486"],"URL":"https:\/\/doi.org\/10.1145\/3394486.3403249","relation":{},"subject":[],"published":{"date-parts":[[2020,8,20]]},"assertion":[{"value":"2020-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}