{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:19:47Z","timestamp":1762237187183,"version":"build-2065373602"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"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":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217842","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"537-543","source":"Crossref","is-referenced-by-count":0,"title":["LatentSpeech: Latent Diffusion for Text-To-Speech Generation"],"prefix":"10.1109","author":[{"given":"Haowei","family":"Lou","sequence":"first","affiliation":[{"name":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hye-Young","family":"Paik","sequence":"additional","affiliation":[{"name":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pari Delir","family":"Haghighi","sequence":"additional","affiliation":[{"name":"Monash University,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo,School of Engineering,Yokohama,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Hu","sequence":"additional","affiliation":[{"name":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lina","family":"Yao","sequence":"additional","affiliation":[{"name":"UNSW Sydney,School of Computer Science and Engineering,Australia,2033"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"Ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3696409.3700163"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"journal-title":"Imagen video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref5"},{"issue":"2","key":"ref6","first-page":"3","volume":"1","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"journal-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref8"},{"volume-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative ai","year":"2023","author":"Zhang","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095100"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00097"},{"volume-title":"Rave: A variational autoencoder for fast and high-quality neural audio synthesis","year":"2021","author":"Caillon","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/78.258122"},{"journal-title":"Ddsp: Differentiable digital signal processing","year":"2020","author":"Engel","key":"ref15"},{"key":"ref16","article-title":"At-tention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"volume-title":"Diffwave: A versatile diffusion model for audio synthesis","year":"2020","author":"Kong","key":"ref17"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"year":"2020","key":"ref19","article-title":"Chinese mandarin female corpus"},{"key":"ref20","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International Conference on Machine Learning","author":"Radford"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2025,8,25]]},"location":"Eindhoven, Netherlands","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217842.pdf?arnumber=11217842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:17:16Z","timestamp":1762237036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217842","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}