{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:06:58Z","timestamp":1767625618484,"version":"3.28.0"},"reference-count":21,"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\/icassp49357.2023.10096279","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":1,"title":["High-Acoustic Fidelity Text To Speech Synthesis With Fine-Grained Control Of Speech Attributes"],"prefix":"10.1109","author":[{"given":"Rafael","family":"Valle","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o Felipe","family":"Santos","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin J.","family":"Shih","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohan","family":"Badlani","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bryan","family":"Catanzaro","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Generative modeling for low dimensional speech attributes with neural spline flows","year":"2022","author":"shih","key":"ref13"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"article-title":"Density estimation using real nvp","year":"2016","author":"dinh","key":"ref15"},{"article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","year":"2018","author":"skerry-ryan","key":"ref14"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref11"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"ref2","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref1","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-335"},{"article-title":"Fastspeech2","year":"2022","author":"chien","key":"ref18"},{"key":"ref8","article-title":"Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis","author":"valle","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref7","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"},{"article-title":"Fastspeech: Fast, robust and controllable text to speech","year":"2019","author":"ren","key":"ref9"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"ren","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref6","article-title":"Rad-tts: Parallel flow-based tts with robust alignment learning and diverse synthesis","author":"shih","year":"2021","journal-title":"ICML Workshop on Invertible Neural Networks Normalizing Flows and Explicit Likelihood Models"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"}],"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\/10096279.pdf?arnumber=10096279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:59:19Z","timestamp":1700506759000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096279\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096279","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}