{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:39:54Z","timestamp":1753601994514,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446859","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11916-11920","source":"Crossref","is-referenced-by-count":2,"title":["Controllable Prosody Generation with Partial Inputs"],"prefix":"10.1109","author":[{"given":"Dan Andrei","family":"Iliescu","sequence":"first","affiliation":[{"name":"University of Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devang S","family":"Ram Mohan","sequence":"additional","affiliation":[{"name":"Papercup Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian Huey","family":"Teh","sequence":"additional","affiliation":[{"name":"Google Deepmind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zack","family":"Hodari","sequence":"additional","affiliation":[{"name":"Papercup Technologies"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.05.014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683501"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139839099"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref4"},{"article-title":"Synthesising prosody with insufficient context","year":"2022","author":"Hodari","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/01690961003589492"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1583"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-019-10163-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"article-title":"Towards coherent image inpainting using denoising diffusion implicit models","volume-title":"International Conference on Machine Learning","author":"Zhang","key":"ref10"},{"article-title":"Recent advances in autoencoder-based representation learning","volume-title":"Third workshop on Bayesian Deep Learning (NeurIPS)","author":"Tschannen","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.006"},{"article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume-title":"NIPS","author":"Hsu","key":"ref13"},{"key":"ref14","first-page":"6264","article-title":"Fully-hierarchical finegrained prosody modeling for interpretable speech synthesis","volume-title":"Proc. International Conference on Speech and Signal Processing","author":"Sun"},{"key":"ref15","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. International Conference on Neural Information Processing Systems","author":"Van den Oord"},{"volume-title":"Rethinking context: Language as an interactive phenomenon","year":"1992","author":"Goodwin","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-43"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1037\/10096-006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-194"},{"key":"ref20","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"Sohn","year":"2015"},{"article-title":"Attention-based deep multiple instance learning","year":"2018","author":"Ilse","key":"ref21"},{"key":"ref22","first-page":"518","article-title":"A robust algorithm for pitch tracking (RAPT)","volume":"495","author":"Talkin","year":"1995","journal-title":"Speech coding and synthesis"},{"article-title":"The kaldi speech recognition toolkit","volume-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding","author":"Daniel","key":"ref23"},{"article-title":"Efficient neural audio synthesis","year":"2018","author":"Kalchbrenner","key":"ref24"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446859.pdf?arnumber=10446859","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:45:57Z","timestamp":1722573957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446859\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446859","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}