{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:27Z","timestamp":1764399087325,"version":"3.46.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249203","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"962-967","source":"Crossref","is-referenced-by-count":0,"title":["ULF-TTS: An Uncluttered Hybrid TTS System Using Language and Flow Matching Models"],"prefix":"10.1109","author":[{"given":"Jae Hyun","family":"Park","sequence":"first","affiliation":[{"name":"NC AI Co., Ltd"}]},{"given":"Seung Jae","family":"Choi","sequence":"additional","affiliation":[{"name":"NC AI Co., Ltd"}]},{"given":"Young Sik","family":"Eom","sequence":"additional","affiliation":[{"name":"NC AI Co., Ltd"}]},{"given":"Allison","family":"Shindell","sequence":"additional","affiliation":[{"name":"NC AI Co., Ltd"}]},{"given":"Min-Gwan","family":"Seo","sequence":"additional","affiliation":[{"name":"NC AI Co., Ltd"}]},{"given":"Gyeong-Hoon","family":"Lee","sequence":"additional","affiliation":[{"name":"NC AI Co., Ltd"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural codec language models are zero-shot text to speech synthesizers","volume-title":"arXiv preprint","author":"Wang","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref3","article-title":"Seed-tts: A family of high-quality versatile speech generation models","volume-title":"arXiv preprint","author":"Anastassiou","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref5","article-title":"High fidelity neural audio compression","volume-title":"arXiv preprint","author":"D\u00e9fossez","year":"2022"},{"key":"ref6","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832320"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"ref11","article-title":"Better speech synthesis through scaling","volume-title":"arXiv preprint","author":"Betker","year":"2023"},{"key":"ref12","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","volume-title":"arXiv preprint","author":"Du","year":"2024"},{"key":"ref13","article-title":"Fireredtts: A foundation text-to-speech framework for industry-level generative speech applications","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832247"},{"key":"ref15","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"},{"key":"ref16","article-title":"Autoregressive speech synthesis without vector quantization","volume-title":"arXiv preprint","author":"Meng","year":"2024"},{"key":"ref17","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","volume-title":"arXiv preprint","author":"Tang","year":"2024"},{"key":"ref18","article-title":"Better & faster large language models via multi-token prediction","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Gloeckle","year":"2025"},{"key":"ref19","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Fortyfirst International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","article-title":"Finite scalar quantization: Vq-vae made simple","volume-title":"arXiv preprint","author":"Mentzer","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref23","article-title":"Understanding ssim","author":"Nilsson","year":"2020","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref26","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref30","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2005"},{"key":"ref32","article-title":"Flow matching for generative modeling","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lipman","year":"2023"},{"key":"ref33","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov","year":"2021"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"volume-title":"The lj speech dataset","year":"2017","author":"Ito","key":"ref35"},{"key":"ref36","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26479"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249203.pdf?arnumber=11249203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:34Z","timestamp":1764399034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249203","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}