{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:50:48Z","timestamp":1778604648034,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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":[[2024,11,7]]},"DOI":"10.1109\/iscslp63861.2024.10800403","type":"proceedings-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:11:17Z","timestamp":1734981077000},"page":"606-610","source":"Crossref","is-referenced-by-count":1,"title":["Expressive Speech Synthesis with Theme-Oriented Few-Shot Learning in ICAGC 2024"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Wang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrui","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Gong","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiuyu","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University,Tianjin Key Laboratory of Cognitive Computing and Application,Tianjin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389766"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/ISCSLP63861.2024.10800374","article-title":"Inspirational and Convincing Audio Generation Challenge 2024 ICAGC 2024","volume-title":"The 14th International Symposium on Chinese Spoken Lan-guage Processing (ISCSLP 2024)","author":"Fu"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414720"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3301217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1297"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-686"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2004-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref11","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Mel-gan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447797"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref20","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3434425"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446203"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3451951"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3167258"},{"key":"ref28","volume-title":"Improving language understanding by generative pretraining","author":"Radford","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-225"},{"key":"ref30","article-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"}],"event":{"name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","location":"Beijing, China","start":{"date-parts":[[2024,11,7]]},"end":{"date-parts":[[2024,11,10]]}},"container-title":["2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799944\/10799969\/10800403.pdf?arnumber=10800403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:26:22Z","timestamp":1735021582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iscslp63861.2024.10800403","relation":{},"subject":[],"published":{"date-parts":[[2024,11,7]]}}}