{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:03:44Z","timestamp":1764403424434,"version":"3.32.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T00:00:00Z","timestamp":1729123200000},"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":[[2024,10,17]]},"DOI":"10.1109\/o-cocosda64382.2024.10800072","type":"proceedings-article","created":{"date-parts":[[2024,12,20]],"date-time":"2024-12-20T18:56:08Z","timestamp":1734720968000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Continual Gated Adapter for Bilingual Codec Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Li-Jen","family":"Yang","sequence":"first","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[{"name":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2679"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1163"},{"key":"ref4","article-title":"Neural codec language mod-els are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"vq-Wav2Vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. of International Conference on Learning Representations","author":"Baevski","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref9","article-title":"High fidelity neural audio compression","author":"Defossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-675"},{"key":"ref11","article-title":"AdaSpeech: Adaptive text to speech for custom voice","volume-title":"Proc. of International Conference on Learning Representations","author":"Chen","year":"2021"},{"key":"ref12","first-page":"6613","article-title":"AdaSpeech 2: Adaptive text to speech with untran-scribed data","volume-title":"Proc. of International Conference on Acous-tics, Speech, and Signal Processing","author":"Yan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1800"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1212"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317410"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389727"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn48605.2020.9207478"},{"key":"ref18","article-title":"Continual speaker adaptation for text-to-speech synthesis","volume-title":"arXiv preprint","author":"Hemati","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-865"},{"key":"ref20","first-page":"230","article-title":"Asymmetric multi-task learning based on task relatedness and loss","volume-title":"Proc. of International Conference on Machine Learning","author":"Lee"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.388"},{"key":"ref22","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. of In-ternational Conference on Machine Learning","author":"Houlsby"},{"article-title":"LibriTTS: A corpus derived from lib-rispeech for text-to-speech","volume-title":"Proc. of Annual Conference of International Speech Communication Association","author":"Zen","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref26","first-page":"670","article-title":"Promoting mental self-disclosure in a spoken dialogue system","volume-title":"Proc. of Annual Conference of International Speech Communication Association","author":"Rohmatillah"},{"key":"ref27","first-page":"1003","article-title":"Reliable dialogue system for facilitating student-counselor communication","volume-title":"Proc. of Annual Conference of International Speech Communication Association","author":"Rohmatillah"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038221"},{"key":"ref29","first-page":"4218","article-title":"Com-mon Voice: A massively-multilingual speech corpus","volume-title":"Proc. of Language Resources and Evaluation Conference","author":"Ardila"},{"key":"ref30","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. of International Conference on Machine Learning","author":"Radford"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3004760"},{"key":"ref32","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402077"}],"event":{"name":"2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2024,10,17]]},"location":"Hsinchu City, Taiwan","end":{"date-parts":[[2024,10,19]]}},"container-title":["2024 27th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10799946\/10799972\/10800072.pdf?arnumber=10800072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,21]],"date-time":"2024-12-21T05:57:54Z","timestamp":1734760674000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10800072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,17]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda64382.2024.10800072","relation":{},"subject":[],"published":{"date-parts":[[2024,10,17]]}}}