{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:43:07Z","timestamp":1762368187059,"version":"build-2065373602"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204217","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Unseen Speaker and Language Adaptation for Lightweight Text-to-Speech with Adapters"],"prefix":"10.1109","author":[{"given":"Alessio","family":"Falai","sequence":"first","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akos","family":"Gangoly","sequence":"additional","affiliation":[{"name":"Amazon AGI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"volume-title":"Better speech synthesis through scaling","year":"2023","author":"Betker","key":"ref1"},{"journal-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383551"},{"journal-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","year":"2023","author":"Zhang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-242"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10115"},{"journal-title":"Cross-lingual text-to-speech with flow-based voice conversion for improved pronunciation","year":"2022","author":"Ellinas","key":"ref10"},{"key":"ref11","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Houlsby","year":"2019"},{"key":"ref12","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2022","journal-title":"International Con-ference on Learning Representations"},{"key":"ref13","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acllong.353"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"ref16","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"journal-title":"Residual adapters for few-shot text-to-speech speaker adaptation","year":"2022","author":"Morioka","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2313"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1568"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-35"},{"key":"ref22","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref24","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Advances in neural information processing systems","volume":"32","author":"Kumar","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095656"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"article-title":"Bs. 1534\u20131. method for the subjective assessment of intermediate sound quality (mushra)","volume-title":"ITUR Recommendation","year":"2001","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3308560.3317084"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-764"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2493525"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2018.8463298"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1616"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1344"},{"key":"ref40","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Baevski","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462635"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2027"},{"key":"ref43","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2019"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","start":{"date-parts":[[2025,8,31]]},"location":"Istanbul, Turkiye","end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204217.pdf?arnumber=11204217","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:35Z","timestamp":1762367855000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204217\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204217","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}