{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T11:17:20Z","timestamp":1760267840850,"version":"3.28.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317116","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1771-1778","source":"Crossref","is-referenced-by-count":2,"title":["ASR Model Adaptation for Rare Words Using Synthetic Data Generated by Multiple Text-To-Speech Systems"],"prefix":"10.1109","author":[{"given":"Kwok Chin","family":"Yuen","sequence":"first","affiliation":[{"name":"Nangyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Haoyang","sequence":"additional","affiliation":[{"name":"Nangyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chng Eng","family":"Siong","sequence":"additional","affiliation":[{"name":"Nangyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639038"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-348"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682816"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053139"},{"key":"ref8","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023072"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7472621"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682738"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462492"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268948"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1392"},{"article-title":"On using monolingual corpora in neural machine translation","year":"2015","author":"Gulcehre","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10037977"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688218"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref26","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":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref30","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"Jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref31","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)"},{"article-title":"Espnet2-tts: Extending the edge of tts research","year":"2021","author":"Hayashi","key":"ref32"},{"volume-title":"Coqui TTS","year":"2021","author":"Eren","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376503"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"Kingma","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"article-title":"Decoupled weight decay regularization","year":"2017","author":"Loshchilov","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383491"},{"article-title":"Searching for activation functions","year":"2017","author":"Ramachandran","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3084827"},{"article-title":"Deep learning using rectified linear units (relu)","year":"2018","author":"Agarap","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2416"},{"key":"ref48","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424251"},{"article-title":"Surgical fine-tuning improves adaptation to distribution shifts","year":"2022","author":"Lee","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317116.pdf?arnumber=10317116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:42:05Z","timestamp":1709404925000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317116\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317116","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}