{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T14:27:14Z","timestamp":1766759234596,"version":"3.30.2"},"reference-count":26,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095131","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":5,"title":["Do Prosody Transfer Models Transfer Prosody?"],"prefix":"10.1109","author":[{"given":"Atli Thor","family":"Sigurgeirsson","sequence":"first","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Char2wav: End-to-end speech synthesis","author":"Sotelo","year":"2017","journal-title":"ICLR"},{"key":"ref2","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"Gibiansky","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/01690961003589492"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.pragma.2005.04.012"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/23273798.2014.963130"},{"key":"ref8","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1113"},{"volume-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","year":"2019","author":"Battenberg","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref15","article-title":"Daft-exprt: Robust prosody transfer across speakers for expressive speech synthesis","author":"Za\u00efdi","year":"2021","journal-title":"arXiv preprint"},{"key":"ref16","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","volume-title":"International Conference on Learning Representations","author":"Valle","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref19","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"International conference on machine learning","author":"Ganin"},{"volume-title":"Parallel audiobook corpus","year":"2018","author":"Ribeiro","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-531"},{"key":"ref22","article-title":"Tadam: Task dependent adaptive metric for improved few-shot learning","volume":"31","author":"Oreshkin","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"}],"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\/10095131.pdf?arnumber=10095131","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T23:56:13Z","timestamp":1733874973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095131\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095131","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}