{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:32:48Z","timestamp":1776882768249,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889180","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Vector Quantized Diffusion Model Based Speech Bandwidth Extension"],"prefix":"10.1109","author":[{"given":"Yuan","family":"Fang","sequence":"first","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinglin","family":"Bai","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajie","family":"Wang","sequence":"additional","affiliation":[{"name":"SenseTime,SenseAuto Intelligent Connection,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University,College of Computer Science,Hohhot,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-36"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446439"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11026"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref8","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"ref10","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref11","author":"D\u00e9fossez","year":"2022","journal-title":"High fidelity neural audio compression"},{"key":"ref12","author":"Yang","year":"2023","journal-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec"},{"key":"ref13","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref15","author":"Tang","year":"2022","journal-title":"Improved vector quantized diffusion models"},{"key":"ref16","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume":"34","author":"Austin","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Gu"},{"key":"ref18","author":"Gu","year":"2023","journal-title":"Mamba: Linear-time sequence modeling with selective state spaces"},{"key":"ref19","article-title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","volume-title":"International Conference on Machine Learning (ICML)","author":"Dao"},{"key":"ref20","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","author":"Devlin","year":"2018","journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref22","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889391"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-994"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3566210"},{"key":"ref26","first-page":"271","article-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-015-0054-9"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889180.pdf?arnumber=10889180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:57Z","timestamp":1774416177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889180","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}