{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:36:38Z","timestamp":1740101798670,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10097204","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Phoneix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation With Phoneme Distribution Predictor"],"prefix":"10.1109","author":[{"given":"Yuning","family":"Wu","sequence":"first","affiliation":[{"name":"Renmin University of China,School of Information"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qian","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Information"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongji","family":"Gao","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Center for Language and Speech Processing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Information"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747422"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596184"},{"key":"ref34","article-title":"An hmm-based system for automatic segmentation and alignment of speech","author":"sj\u00f6lander","year":"2003","journal-title":"Proceedings of Fonetik"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053944"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1410"},{"key":"ref31","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"NeurIPS"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"article-title":"MR-SVS: Singing voice synthesis with multi-reference encoder","year":"2022","author":"wang","key":"ref11"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1563"},{"key":"ref32","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414348"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/3680822"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-239"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892111"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414043"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1575"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747664"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659797"},{"article-title":"Singing voice synthesis based on convolutional neural networks","year":"2019","author":"nakamura","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-454"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362104"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3552466.3556534"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10039"},{"article-title":"DB Production: Futon P","year":"0","author":"futon","key":"ref27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-48"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"article-title":"Hifisinger: Towards high-fidelity neural singing voice synthesis","year":"2020","author":"chen","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3104165"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403249"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-978"},{"key":"ref6","article-title":"Recent development of the hmm-based singing voice synthesis system—sinsy","author":"oura","year":"2010","journal-title":"ISCA Workshop on Speech Synthesis"},{"key":"ref5","article-title":"Karaoker: Alignment-free singing voice synthesis with speech training data","author":"panos","year":"2022","journal-title":"InterSpeech"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10097204.pdf?arnumber=10097204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:20Z","timestamp":1700507360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097204","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}