{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:37:58Z","timestamp":1781714278585,"version":"3.54.5"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094992","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":86,"title":["TF-GRIDNET: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation"],"prefix":"10.1109","author":[{"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shukjae","family":"Choi","sequence":"additional","affiliation":[{"name":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Younglo","family":"Lee","sequence":"additional","affiliation":[{"name":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"653","article-title":"FurcaNeXt: End-to-End Monaural Speech Separation with Dynamic Gated Dilated Temporal Convolutional Networks","author":"zhang","year":"2020","journal-title":"Proc ICMMT"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129363"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054719"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3083405"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145319"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref33","article-title":"Leveraging Low-Distortion Target Estimates for Improved Speech Enhancement","author":"wang","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2290"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-149"},{"key":"ref16","first-page":"7121","article-title":"Voice Separation with An Unknown Number of Multiple Speakers","author":"nachmani","year":"2020","journal-title":"ICML"},{"key":"ref38","first-page":"626","article-title":"SDR – Half-Baked or Well Doneƒ","author":"le roux","year":"2019","journal-title":"Proc ICASSP"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIS53528.2021.9645957"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-700"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-986"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21372"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747554"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413837"},{"key":"ref42","article-title":"Voice and Accompaniment Separation in Music using Self-Attention Convolutional Neural Network","author":"liu","year":"2020"},{"key":"ref41","article-title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","volume":"32","author":"paszke","year":"2019","journal-title":"Proc NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746882"},{"key":"ref44","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-296"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"ref9","first-page":"697","article-title":"TasNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation","author":"luo","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10727"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094992.pdf?arnumber=10094992","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:02:19Z","timestamp":1700506939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094992\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094992","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}