{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:56:10Z","timestamp":1776887770951,"version":"3.51.2"},"reference-count":33,"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\/icassp49660.2025.10889396","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["AdaptVC: High Quality Voice Conversion with Adaptive Learning"],"prefix":"10.1109","author":[{"given":"Jaehun","family":"Kim","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ji-Hoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeunju","family":"Choi","sequence":"additional","affiliation":[{"name":"Samsung Research,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":"Seongkyu","family":"Mun","sequence":"additional","affiliation":[{"name":"Samsung Research,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","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone","volume-title":"Proc. ICML","author":"Casanova"},{"key":"ref2","article-title":"VoiceMixer: Adversarial Voice Style Mixup","author":"Lee","year":"2021","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022787"},{"key":"ref4","article-title":"AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss","volume-title":"Proc. ICML","author":"Qian"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref6","article-title":"Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme","volume-title":"Proc. ICLR","author":"Popov"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref8","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref11","article-title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","author":"Choi","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29740"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref14","article-title":"Parameter-Efficient Transfer Learning for NLP","volume-title":"Proc. ICML","author":"Houlsby"},{"key":"ref15","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"ref17","article-title":"Flow Matching for Generative Modeling","volume-title":"Proc. ICLR","author":"Lipman"},{"key":"ref18","article-title":"Vector-Quantized Image Modeling with Improved VQGAN","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref19","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref20","article-title":"NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis","volume-title":"Proc. ICLR","author":"Choi"},{"key":"ref21","article-title":"Encoding Speaker-Specific Latent Speech Feature for Speech Synthesis","volume-title":"Proc. ICML","author":"Kong"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref26","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref27","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","author":"Kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref29","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447809"},{"key":"ref32","article-title":"Investigating the\u2019Autoencoder Behavior\u2019in Speech Self-Supervised Models: a focus on HuBERT\u2019s Pretraining","author":"Vielzeuf","year":"2024"},{"key":"ref33","article-title":"Meta-stylespeech : Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. ICML","author":"Min"}],"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\/10889396.pdf?arnumber=10889396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:48Z","timestamp":1774416408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889396","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}