{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:38:51Z","timestamp":1776886731169,"version":"3.51.2"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230923","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration"],"prefix":"10.1109","author":[{"given":"Shigeki","family":"Karita","sequence":"first","affiliation":[{"name":"Google DeepMind,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuma","family":"Koizumi","sequence":"additional","affiliation":[{"name":"Google DeepMind,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[{"name":"Google DeepMind,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haruko","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"Google DeepMind,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robin","family":"Scheibler","sequence":"additional","affiliation":[{"name":"Google DeepMind,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michiel","family":"Bacchiani","sequence":"additional","affiliation":[{"name":"Google DeepMind,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937165"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-298"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11026"},{"key":"ref5","author":"Serr\u00e0","year":"2022","journal-title":"Universal speech enhancement with score-based diffusion"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2024.3445871"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-138"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2025.acl-long.651","article-title":"LLaSE-G1: Incentivizing generalization capability for llama-based speech enhancement","author":"Kang","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-590"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890760"},{"key":"ref13","article-title":"DiTSE: High-fidelity generative speech enhancement via latent diffusion transformers","author":"Guimar\u00e3es","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1356"},{"key":"ref16","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","year":"2024"},{"key":"ref17","article-title":"GPT-4 technical report","year":"2024"},{"key":"ref18","article-title":"Moshi: a speech-text foundation model for real-time dialogue","author":"D\u00e9fossez","year":"2024"},{"key":"ref19","article-title":"Google USM: Scaling automatic speech recognition beyond 100 languages","author":"Zhang","year":"2023"},{"key":"ref20","article-title":"Towards a unified view of parameter-efficient transfer learning","volume-title":"ICLR","author":"He"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022496"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"ref23","article-title":"Self-supervised learning with random-projection quantizer for speech recognition","volume-title":"ICML","author":"Chiu"},{"key":"ref24","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3122291"},{"key":"ref27","article-title":"Wavlm: Large-scale self-supervised pre-training for full stack speech processing","author":"Chen","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-419"},{"key":"ref29","article-title":"Vec-tok speech: speech vectorization and tokenization for neural speech generation","author":"Zhu","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2880284"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref33","article-title":"WaveGrad: Estimating gradients for waveform generation","volume-title":"ICLR","author":"Chen"},{"key":"ref34","article-title":"URGENT challenge 2025 baseline","author":"Saijo","year":"2025"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448173"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref37","article-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations","author":"Lyth","year":"2024"},{"key":"ref38","first-page":"4197","article-title":"CoVoST: A diverse multilingual speech-to-text translation corpus","volume-title":"LREC","author":"Wang"},{"key":"ref39","first-page":"6691","article-title":"CVSS corpus and massively multilingual speech-to-speech translation","volume-title":"LREC","author":"Jia"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref45","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"NeurIPS","author":"Jia","year":"2018"},{"key":"ref46","article-title":"Sample efficient adaptive text-to-speech","volume-title":"ICLR","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10094909"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref50","article-title":"The design for the Wall Street Journal-based CSR corpus","volume-title":"Speech and Natural Language: Proceedings of a Workshop Held at Harriman, New York, February 23-26, 1992","author":"Paul"},{"key":"ref51","article-title":"Common Voice: A massively-multilingual speech corpus","volume-title":"LREC","author":"Ardila"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-938"},{"key":"ref53","first-page":"10205","article-title":"Towards robust speech representation learning for thousands of languages","volume-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","author":"Chen"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230923.pdf?arnumber=11230923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:23Z","timestamp":1763191943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230923","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}