{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:26:16Z","timestamp":1762237576743,"version":"build-2065373602"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"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":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217801","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"551-556","source":"Crossref","is-referenced-by-count":0,"title":["Parameter-Efficient Personalized Speech Synthesis via EMD-based Speaker Modeling"],"prefix":"10.1109","author":[{"given":"Chengxi","family":"Lei","sequence":"first","affiliation":[{"name":"Massey University,School of Mathematical and Computational Sciences,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Hou","sequence":"additional","affiliation":[{"name":"Massey University,School of Mathematical and Computational Sciences,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huia","family":"Jahnke","sequence":"additional","affiliation":[{"name":"Massey University,School of Māori and Multicultural Education,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[{"name":"Massey University,School of Mathematical and Computational Sciences,New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s13198-022-01709-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-022-00913-x"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref4","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393714"},{"key":"ref6","article-title":"Neural voice cloning with a few samples","volume":"31","author":"Arik","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3308374"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054301"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097178"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref13","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","article-title":"Close to human quality tts with transformer","volume":"2","author":"Li","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-021-08899-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.02.040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-5747-4_27"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.09.002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-019-0169-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbe.2020.12.009"},{"key":"ref21","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume":"35","author":"Lian","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Multi-task learning using uncertainty to weigh losses for heterogeneous face attribute estimation","year":"2024","author":"Yuan","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-729"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref24"},{"key":"ref25","first-page":"17 022","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747388"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2025,8,25]]},"location":"Eindhoven, Netherlands","end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217801.pdf?arnumber=11217801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:22:01Z","timestamp":1762237321000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217801","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}