{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:10:32Z","timestamp":1781050232785,"version":"3.54.1"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["JP23K16944"],"award-info":[{"award-number":["JP23K16944"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3451982","type":"journal-article","created":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T17:32:22Z","timestamp":1725384742000},"page":"3924-3933","source":"Crossref","is-referenced-by-count":3,"title":["Refining Synthesized Speech Using Speaker Information and Phone Masking for Data Augmentation of Speech Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2255-3154","authenticated-orcid":false,"given":"Sei","family":"Ueno","sequence":"first","affiliation":[{"name":"Nagoya Institute of Technology, Nagoya-shi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5323-9191","authenticated-orcid":false,"given":"Akinobu","family":"Lee","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology, Nagoya-shi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2686-2296","authenticated-orcid":false,"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref2","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Graves","year":"2014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-350"},{"key":"ref4","first-page":"604","article-title":"Acoustic modelling with CD-CTC-SMBR LSTM RNNs","volume-title":"Proc. IEEE Autom. Speech Recognit. Understanding Workshop","author":"Sak","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268937"},{"key":"ref6","first-page":"1","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst. Workshop Deep Learn.","author":"Chorowski","year":"2014"},{"key":"ref7","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-232"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"ref14","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268951"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639589"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682816"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1475"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2920"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI51763.2020.9263564"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1882"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1656"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746217"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746582"},{"key":"ref31","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Ren","year":"2019"},{"key":"ref32","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1461"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8461368"},{"key":"ref36","article-title":"Wavenet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref37","first-page":"2410","article-title":"Efficient neural audio synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kalchbrenner","year":"2018"},{"key":"ref38","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Kumar","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref40","first-page":"1","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref41","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-962"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/sibircon48586.2019.8957862"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-409"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053182"},{"key":"ref47","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Gibiansky","year":"2017"},{"key":"ref48","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1778"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10664004.pdf?arnumber=10664004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T04:03:25Z","timestamp":1725768205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10664004\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3451982","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}