{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:14:48Z","timestamp":1791911688131,"version":"4.3.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747441","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"956-960","source":"Crossref","is-referenced-by-count":2,"title":["KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE Using Mel-Spectrograms"],"prefix":"10.1109","author":[{"given":"Chien-Feng","family":"Liao","sequence":"first","affiliation":[{"name":"Taiwan AI Labs,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jen-Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Taiwan AI Labs,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Taiwan AI Labs,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","article-title":"The curious case of neural text degeneration","author":"holtzman","year":"2020","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref33","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref31","article-title":"DiscreTalk: Text-to-speech as a machine translation problem","author":"hayashi","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref37","article-title":"The CMU pronouncing dictionary","year":"0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054567"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1936"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1518"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref11","article-title":"HiFiSinger: Towards high-fidelity neural singing voice synthesis","author":"chen","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref13","article-title":"A survey on neural speech synthesis","author":"tan","year":"2021"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1722"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1399"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref28","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-872"},{"key":"ref27","article-title":"Predicting video with VQVAE","author":"walker","year":"2021"},{"key":"ref3","first-page":"4009","article-title":"VOCALOID-commercial singing synthesizer based on sample concatenation","author":"kenmochi","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref6","article-title":"Recent development of the HMM-based singing voice synthesis system—Sinsy","author":"oura","year":"2010","journal-title":"Proc ISCA Workshop on Speech Synthesis"},{"key":"ref29","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-584"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/AIVR52153.2021.00067"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053811"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/3680822"},{"key":"ref20","article-title":"Score and lyrics-free singing voice generation","author":"liu","year":"2020","journal-title":"Proc Int Conf Computational Creativity"},{"key":"ref22","article-title":"Jukebox: A generative model for music","author":"dhariwal","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1137"},{"key":"ref24","first-page":"2390","article-title":"Fast decoding in sequence models using discrete latent variables","author":"kaiser","year":"2018","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref23","article-title":"Neural discrete representation learning","author":"oord","year":"2017","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref25","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","author":"razavi","year":"2019","journal-title":"Proc Advances in Neural Information Processing Systems"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747441.pdf?arnumber=9747441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:10:34Z","timestamp":1660579834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747441","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}