{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:15Z","timestamp":1774420095716,"version":"3.50.1"},"reference-count":37,"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"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010238","name":"K2","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010238","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889369","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers"],"prefix":"10.1109","author":[{"given":"Nohil","family":"Park","sequence":"first","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Heeseung","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Che Hyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Jooyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Jiheum","family":"Yeom","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Sungroh","family":"Yoon","sequence":"additional","affiliation":[{"name":"Seoul National University,ECE, AIIS, ASRI, INMC, ISRC, and IPAI,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Popov"},{"key":"ref2","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Kim"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref5","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shen"},{"key":"ref6","article-title":"P-flow: A fast and data-efficient zero-shot TTS through speech prompting","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Kim"},{"key":"ref7","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Forty-first International Conference on Machine Learning","author":"Ju"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414872"},{"key":"ref9","article-title":"Neural voice cloning with a few samples","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Arik","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2313"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393714"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref14","article-title":"Guided-tts 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref16","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-63"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref19","article-title":"LLaMA-adapter: Efficient fine-tuning of large language models with zero-initialized attention","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref21","first-page":"521","article-title":"Orca: A distributed serving system for Transformer-Based generative models","volume-title":"16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu"},{"key":"ref22","article-title":"Batched low-rank adaptation of foundation models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref24","article-title":"Mix-of-show: Decentralized low-rank adaptation for multi-concept customization of diffusion models","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Gu"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ho","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","article-title":"DoRA: Weight-decomposed low-rank adaptation","volume-title":"Forty-first International Conference on Machine Learning","author":"yang Liu"},{"key":"ref28","article-title":"VeRA: Vector-based random matrix adaptation","volume-title":"The Twelfth International Conference on Learning Representations","author":"Kopiczko"},{"key":"ref29","article-title":"RoSA: Accurate parameter-efficient fine-tuning via robust adaptation","volume-title":"Forty-first International Conference on Machine Learning","author":"Nikdan"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref31","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref33","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"The Eleventh International Conference on Learning Representations","author":"gil Lee"},{"key":"ref34","article-title":"Resemblyzer","author":"Louppe","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref36","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.994"}],"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\/10889369.pdf?arnumber=10889369","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:22Z","timestamp":1774416382000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889369\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889369","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}