{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T08:28:40Z","timestamp":1788164920934,"version":"build-2803163510"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414408","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"6598-6602","source":"Crossref","is-referenced-by-count":20,"title":["TTS-by-TTS: TTS-Driven Data Augmentation for Fast and High-Quality Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Min-Jae","family":"Hwang","sequence":"first","affiliation":[{"name":"Search Solutions Inc.,Seongnam,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryuichi","family":"Yamamoto","sequence":"additional","affiliation":[{"name":"LINE Corp.,Tokyo,Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunwoo","family":"Song","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae-Min","family":"Kim","sequence":"additional","affiliation":[{"name":"NAVER Corp.,Seongnam,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref10","first-page":"470","article-title":"Improved Parallel WaveGAN vocoder with perceptually weighted spectrogram loss","author":"song","year":"2021","journal-title":"Proc SLT"},{"key":"ref11","article-title":"Parallel waveform synthesis based on generative adversarial networks with voicing-aware conditional discriminators","author":"yamamoto","year":"2021","journal-title":"Proc ICASSP (in press)"},{"key":"ref12","article-title":"You do not need more data: Improving end-to-end speech recognition by text-to-speech data augmentation","author":"laptev","year":"2020","journal-title":"ArXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683343"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1437"},{"key":"ref15","first-page":"3915","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","author":"van den oord","year":"2018","journal-title":"Proc ICML"},{"key":"ref16","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015","journal-title":"Proc NIPS"},{"key":"ref17","article-title":"Mixture density networks","author":"bishop","year":"1994","journal-title":"Tech Rep"},{"key":"ref18","author":"quatieri","year":"2006","journal-title":"Discrete-Time Speech Signal Processing Principles and Practice"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.21437\/Interspeech.2017-314","article-title":"Speaker-dependent WaveNet vocoder","author":"tamamori","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref28","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Proc NIPS"},{"key":"ref4","article-title":"Fast-Speech 2: Fast and high-quality end-to-end text-to-speech","author":"ren","year":"2021","journal-title":"Proc ICLR (in press)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2746264"},{"key":"ref3","first-page":"3165","article-title":"FastSpeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Proc NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003956"},{"key":"ref29","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref5","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"2019","journal-title":"Proc ICLR"},{"key":"ref8","first-page":"810","article-title":"LP-WaveNet: Linear prediction-based WaveNet speech synthesis","author":"hwang","year":"2020","journal-title":"Proc APSIPA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv"},{"key":"ref22","article-title":"FastPitch: Parallel text-to-speech with pitch prediction","author":"la?cucki","year":"2021","journal-title":"Proc ICASSP (in press)"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi","author":"mcauliffe","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref24","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc AISTATS"},{"key":"ref23","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.65"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ArXiv"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414408.pdf?arnumber=9414408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:24Z","timestamp":1659486024000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414408","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}