{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:31:34Z","timestamp":1776889894452,"version":"3.51.2"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248089","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T13:31:37Z","timestamp":1694784697000},"page":"1-5","source":"Crossref","is-referenced-by-count":25,"title":["Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations"],"prefix":"10.1109","author":[{"given":"Yuma","family":"Koizumi","sequence":"first","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shigeki","family":"Karita","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Ding","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Yatabe","sequence":"additional","affiliation":[{"name":"Tokyo University of Agriculture & Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuyuki","family":"Morioka","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Bapna","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michiel","family":"Bacchiani","sequence":"additional","affiliation":[{"name":"Google,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref12","article-title":"Audio super resolution using neural networks","author":"kuleshov","year":"2017","journal-title":"ICLRE"},{"key":"ref34","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1789"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-36"},{"key":"ref31","article-title":"WaveGrad: Estimating gradients for waveform generation","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178801"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/JSTSP.2020.3042071","article-title":"A survey and an extensive evaluation of popular audio declipping methods","author":"z\u00e1vi\u0161ka","year":"2021","journal-title":"IEEE J Sel Top Signal Process"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-298"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937165"},{"key":"ref17","article-title":"BigVGAN: A universal neural vocoder with large-scale training","author":"lee","year":"2023","journal-title":"ICLRE"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"ref16","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"chan","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-641"},{"key":"ref19","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022496"},{"key":"ref24","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"hsu","year":"2019","journal-title":"ICLRE"},{"key":"ref46","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ICML"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref45","article-title":"Non-attentive Tacotron: Robust and control-lable neural TTS synthesis including unsupervised duration modeling","author":"shen","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-194"},{"key":"ref48","article-title":"The LJ speech dataset","author":"ito","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref42","article-title":"Pushing the limits of semi-supervised learning for automatic speech recognition","author":"zhang","year":"2020","journal-title":"NeurIPS SAS 2020 Workshop"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref22","article-title":"Common Voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"LREC"},{"key":"ref44","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2019","journal-title":"ICLRE"},{"key":"ref21","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","author":"chiu","year":"2022","journal-title":"ICML"},{"key":"ref43","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NeurIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1757"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854479"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-733"},{"key":"ref4","article-title":"VoiceFixer: Toward general speech restoration with neural vocoder","author":"liu","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref5","article-title":"Universal speech enhancement with score-based diffusion","author":"serr\u00e0","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2023,10,22]]},"end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248089.pdf?arnumber=10248089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T13:41:00Z","timestamp":1696254060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248089\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248089","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}