{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:12:35Z","timestamp":1774627955912,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"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":[[2024,8,4]]},"DOI":"10.1109\/ialp63756.2024.10661192","type":"proceedings-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T18:23:27Z","timestamp":1725992607000},"page":"401-405","source":"Crossref","is-referenced-by-count":6,"title":["A Mel Spectrogram Enhancement Paradigm Based on CWT in Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Guoqiang","family":"Hu","sequence":"first","affiliation":[{"name":"Jinan University,International School,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaning","family":"Tan","sequence":"additional","affiliation":[{"name":"Jinan University,International School,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruilai","family":"Li","sequence":"additional","affiliation":[{"name":"Jinan University,International School,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.395275"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref5","article-title":"Comsl: A composite speech-language model for end-to-end speech-to-text translation","volume":"36","author":"Le","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/18.119724"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446063"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref10","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref11","article-title":"Mel-spectrogram augmentation for sequence to sequence voice conversion","author":"Hwang","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2938007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/5.488698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/18.119727"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compstruct.2023.117091"},{"key":"ref17","article-title":"Multi-task learning as multi-objective optimization","volume":"31","author":"Sener","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/ecja.4400660203"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803537"},{"key":"ref20","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"issue":"2000","key":"ref21","first-page":"32","article-title":"High-dimensional data analysis: The curses and blessings of dimensionality","volume":"1","author":"Donoho","year":"2000","journal-title":"AMS math challenges lecture"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-86940-2_10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"}],"event":{"name":"2024 International Conference on Asian Language Processing (IALP)","location":"Hohhot, China","start":{"date-parts":[[2024,8,4]]},"end":{"date-parts":[[2024,8,6]]}},"container-title":["2024 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10660661\/10660673\/10661192.pdf?arnumber=10661192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T09:09:33Z","timestamp":1726045773000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10661192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ialp63756.2024.10661192","relation":{},"subject":[],"published":{"date-parts":[[2024,8,4]]}}}