{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:51:23Z","timestamp":1781815883444,"version":"3.54.5"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"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":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389670","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:38:40Z","timestamp":1705671520000},"page":"1-8","source":"Crossref","is-referenced-by-count":2,"title":["MBTFNET: Multi-Band Temporal-Frequency Neural Network for Singing Voice Enhancement"],"prefix":"10.1109","author":[{"given":"Weiming","family":"Xu","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhouxuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhili","family":"Tan","sequence":"additional","affiliation":[{"name":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubo","family":"Lv","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runduo","family":"Han","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Lyra Lab, Tencent Music Entertainment,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xi’an,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref3","article-title":"Phaseaware speech enhancement with deep complex u-net","volume-title":"International Conference on Learning Representations","author":"Choi"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2537"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3079813"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683385"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746610"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747647"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3038"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1609"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747521"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-694"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747765"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1397"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref20","article-title":"Music source separation in the waveform domain","author":"D\u00e9fossez","year":"2019","journal-title":"arXiv preprint arXiv:1911.13254"},{"key":"ref21","article-title":"Decoupling magnitude and phase estimation with deep resunet for music source separation","volume-title":"International Society for Music Information Retrieval Conference","author":"Kong"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362081"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref24","article-title":"Cws-presunet: Music source separation with channel-wise subband phase-aware resunet","author":"Liu","year":"2021","journal-title":"arXiv preprint arXiv:2112.04685"},{"key":"ref25","article-title":"The musdb18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref27","article-title":"Multirate systems and filter banks","author":"Vaidyanathan","year":"1993","journal-title":"Prentice Hall Signal Processing Series"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1482"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref31","article-title":"M4singer: A multistyle, multi-singer and musical score provided mandarin singing corpus","volume-title":"Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zhang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747612"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389670.pdf?arnumber=10389670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:03:33Z","timestamp":1781813013000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389670","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}