{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:57:22Z","timestamp":1730199442305,"version":"3.28.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389773","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech"],"prefix":"10.1109","author":[{"given":"Nicholas","family":"Sanders","sequence":"first","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Korin","family":"Richmond","sequence":"additional","affiliation":[{"name":"University of Edinburgh,The Centre for Speech Technology Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref2","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":"ref3","article-title":"Semi-supervised generative modeling for controllable speech synthesis","author":"Habib","year":"2019","journal-title":"arXiv preprint arXiv:1910.01709"},{"key":"ref4","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-883"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2918"},{"key":"ref7","first-page":"17","article-title":"Expressive neural voice cloning","volume-title":"Proceedings of The 13th Asian Conference on Machine Learning","volume":"157","author":"Neekhara"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/bf02342617"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/23273798.2019.1587482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.conll-1.42"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(90)90081-J"},{"article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal","key":"ref13"},{"key":"ref14","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"},{"article-title":"Adam: A method for stochastic optimization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma","key":"ref15"},{"article-title":"Large batch optimization for deep learning: Training BERT in 76 minutes","volume-title":"International Conference on Learning Representations","author":"You","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"year":"2014","key":"ref18","article-title":"The CMU pronouncing dictionary"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389773.pdf?arnumber=10389773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:32:48Z","timestamp":1706027568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389773","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}