{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:39:04Z","timestamp":1730198344840,"version":"3.28.0"},"reference-count":37,"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\/apsipaasc58517.2023.10317120","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1760-1765","source":"Crossref","is-referenced-by-count":1,"title":["Synthetic Data Augmentation for ASR with Domain Filtering"],"prefix":"10.1109","author":[{"given":"Tuan","family":"Vu Ho","sequence":"first","affiliation":[{"name":"Hitachi, Ltd. Research & Development Group,Japan"}]},{"given":"Shota","family":"Horiguchi","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd. Research & Development Group,Japan"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Paola","family":"Garcia","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,USA"}]},{"given":"Takashi","family":"Sumiyoshi","sequence":"additional","affiliation":[{"name":"Hitachi, Ltd. Research & Development Group,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1465"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461771"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639655"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707748"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-207"},{"key":"ref11","first-page":"21","article-title":"Vocal tract length perturbation (VTLP) improves speech recognition","volume-title":"Proc. ICML Workshop on Deep Learning for Audio, Speech and Language","volume":"117","author":"Jaitly"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682816"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053139"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9414778"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1882"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref24","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. ICML","author":"Kim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1203"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-770"},{"key":"ref28","first-page":"1234","article-title":"Sequence-to-sequence data augmentation for dialogue language understanding","volume-title":"Proc. ICCL","author":"Hou"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.14618\/IDS-PUB-9021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1571"},{"key":"ref36","first-page":"51","article-title":"A non-expert Kaldi recipe for Vietnamese speech recognition system","volume-title":"Proc. Third International Workshop on Worldwide Language Service Infrastructure and Second Workshop on Open Infrastructures and Analysis Frameworks for Human Language Technologies","author":"Luong"},{"key":"ref37","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"}],"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\/10317120.pdf?arnumber=10317120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:42:18Z","timestamp":1709404938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317120","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}