{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T07:15:09Z","timestamp":1778397309623,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688218","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"68-75","source":"Crossref","is-referenced-by-count":14,"title":["Data Augmentation for ASR Using TTS Via a Discrete Representation"],"prefix":"10.1109","author":[{"given":"Sei","family":"Ueno","sequence":"first","affiliation":[{"name":"Graduate School of Informatics, Kyoto University,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinsuke","family":"Sakai","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Kyoto University,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","first-page":"5206","article-title":"Librispeech: An asr corpus based on public domain au-dio books","author":"panayotov","year":"0","journal-title":"IEEE International Conference on Acous-tics Speech and Signal Processing (ICASSP)"},{"key":"ref37","article-title":"On using monolingual corpora in neural machine translation","author":"gulcehre","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref34","first-page":"3935","article-title":"Enhancing the TED-LIUM corpus with selected data for language modeling and more TED talks","author":"rousseau","year":"0","journal-title":"Proc Int Conference on Language Resources and Evaluation (LREC)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639619"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1930"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415058"},{"key":"ref13","first-page":"477","article-title":"Leveraging sequence-to-sequence speech synthesis for enhancing acoustic-to-word speech recog-nition","author":"mimura","year":"0","journal-title":"Proc of the IEEE Workshop on Spoken Language Technology (SLT)"},{"key":"ref14","first-page":"6161","article-title":"Multi-speaker sequence-to-sequence speech synthesis for data augmentation in acoustic-to-word speech recog-nition","author":"ueno","year":"0","journal-title":"IEEE International Conference on Acous-tics Speech and Signal Processing (ICASSP)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053008"},{"key":"ref17","first-page":"556","article-title":"Improving Speech Recog-nition Using GAN-Based Speech Synthesis and Con-trastive Unspoken Text Selection","author":"chen","year":"0","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053831"},{"key":"ref19","first-page":"2832","article-title":"SCADA: Stochastic, Con-sistent and Adversarial Data Augmentation to Improve ASR","author":"wang","year":"2020","journal-title":"InterSpeech"},{"key":"ref28","first-page":"2962","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"gibiansky","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref4","first-page":"5884","article-title":"Speech-transformer: a no-recurrence sequence-to-sequence","author":"dong","year":"0","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref27","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"0","journal-title":"International Conference on Learning Representations (ICRL)"},{"key":"ref3","first-page":"206","article-title":"Ex-ploring neural transducers for end-to-end speech recog-nition","author":"battenberg","year":"0","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1392"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414718"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1554"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"523","DOI":"10.21437\/Interspeech.2017-343","article-title":"Towards better decoding and language model integration in sequence to sequence models","author":"chorowski","year":"2017","journal-title":"InterSpeech"},{"key":"ref9","first-page":"301","article-title":"Listening while speaking: Speech chain by deep learning","author":"tjandra","year":"0","journal-title":"Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU)"},{"key":"ref1","first-page":"369","article-title":"Connectionist Temporal Classification: Labelling Un-segmented Sequence Data with Recurrent Neural Net-works","author":"graves","year":"0","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414778"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref21","article-title":"SynthASR: Unlocking Syn-thetic Data for Speech Recognition","author":"fazel","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref24","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"0","journal-title":"International Conference for Learning Repre sentations (ICLR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref26","article-title":"Neu-ral discrete representation learning","author":"van den oord","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref25","article-title":"wav2vec: Unsupervised pre-training for speech recog-nition","author":"schneider","year":"2019","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688218.pdf?arnumber=9688218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:41:31Z","timestamp":1652733691000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688218","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}