{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:00:46Z","timestamp":1776956446188,"version":"3.51.4"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317485","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"1937-1942","source":"Crossref","is-referenced-by-count":1,"title":["Speech Enhancement with Multi-granularity Vector Quantization"],"prefix":"10.1109","author":[{"given":"Xiaoying","family":"Zhao","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC),Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiushi","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC),NERC-SLIP,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeping","family":"Zhou","sequence":"additional","affiliation":[{"name":"China Merchants Bank"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiqi","family":"Liu","sequence":"additional","affiliation":[{"name":"China Merchants Bank"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2528171"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3275033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138675"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2986896"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1620"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659692"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref12","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume-title":"Proc. of NIPS","volume":"32","author":"Razavi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-489"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-277"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10084"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980218"},{"key":"ref18","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. of NIPS","volume":"33","author":"Baevski"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-67"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref21","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Int. Conf. Machine Learning (ICML)","volume":"162","author":"Baevski"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747379"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746303"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10002"},{"key":"ref25","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref27","article-title":"Improved speech enhancement with the wave-u-net","author":"Macartney","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3025020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref30","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume-title":"Int. Conf. Machine Learning (ICML)","volume":"97","author":"Fu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987441"},{"key":"ref32","article-title":"Noisy speech database for training speech enhancement algorithms and tts models","author":"Valentini-Botinhao","year":"2017"},{"key":"ref33","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","author":"Recommendation","year":"2001","journal-title":"Rec. ITU-T P. 862"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,10,31]]},"end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317485.pdf?arnumber=10317485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T19:00:38Z","timestamp":1709406038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317485\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317485","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}