{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:27:07Z","timestamp":1776889627245,"version":"3.51.2"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890322","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Jaemin","family":"Jung","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junseok","family":"Ahn","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaeyoung","family":"Jung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tan Dat","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjoon","family":"Jang","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref2","article-title":"Audiogen: Textually guided audio generation","volume-title":"Proc. ICLR","author":"Kreuk"},{"key":"ref3","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref4","article-title":"Text-to-audio generation using instruction-tuned llm and latent diffusion model","volume-title":"Proc. ACM MM","author":"Ghosal"},{"key":"ref5","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"Proc. ICML","author":"Evans"},{"key":"ref6","article-title":"Audiolcm: Text-to-audio generation with latent consistency models","volume-title":"Proc. ACM MM","author":"Liu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"key":"ref8","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref9","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","author":"Kim"},{"key":"ref10","article-title":"Guided-tts: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.508"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096929"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447251"},{"key":"ref14","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. ICML","author":"Ju"},{"key":"ref15","article-title":"Ditto-tts: Efficient and scalable zero-shot text-to-speech with diffusion transformer","author":"Lee","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref19","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448268"},{"key":"ref21","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref23","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"},{"key":"ref24","article-title":"Large-scale contrastive language-audio pretraining with feature fusionand keyword-to-caption augmentation","volume-title":"Proc. ICASSP","author":"Wu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref26","article-title":"Common voice: A massively-multilingual speech corpus","author":"Ardila","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446300"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096596"},{"key":"ref33","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref36","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref40","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref41","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","author":"Kong"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1345"},{"key":"ref44","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref45","article-title":"Fr\\\u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890322.pdf?arnumber=10890322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:52Z","timestamp":1774416352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890322\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890322","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}