{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:29:52Z","timestamp":1782966592075,"version":"3.54.5"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"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":[[2021,10,17]]},"DOI":"10.1109\/waspaa52581.2021.9632794","type":"proceedings-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T16:12:28Z","timestamp":1639411948000},"page":"161-165","source":"Crossref","is-referenced-by-count":32,"title":["DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Yuma","family":"Koizumi","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shigeki","family":"Karita","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Scott","family":"Wisdom","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hakan","family":"Erdogan","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John R.","family":"Hershey","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Llion","family":"Jones","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michiel","family":"Bacchiani","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref31","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"0","journal-title":"Proc Int Conf Machine Learn (ICML)"},{"key":"ref30","author":"tay","year":"2020","journal-title":"Efficient transformers A survey"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053266"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1673"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref15","article-title":"Unsupervised sound separation using mixture invariant training","author":"wisdom","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref17","article-title":"At-tention is all you need in speech separation","author":"subakan","year":"0","journal-title":"Proc Int Conf on Acoust Speech and Signal Process (ICASSP)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053038"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461850"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842156"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref29","author":"chen","year":"2020","journal-title":"Continuous speech separation with Conformer"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref8","article-title":"Into the wild with AudioScope: Unsupervised audio-visual separation of on-screen sounds","author":"tzinis","year":"0","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2980956"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415105"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413580"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414841"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref24","article-title":"Conformer-based id-aware autoencoder for unsupervised anomalous sound detection","author":"hayashi","year":"2020","journal-title":"DCASE2020 Challenge Tech Rep"},{"key":"ref23","article-title":"Conformer-based sound event detection with semi-supervised learning and data augmentation","author":"miyazaki","year":"0","journal-title":"Proc Detect Classif Acoust Scenes Events Workshop (DCASE)"},{"key":"ref26","article-title":"Rethinking attention with performers","author":"choromanski","year":"0","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref25","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"}],"event":{"name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2021,10,17]]},"end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9632687\/9632666\/09632794.pdf?arnumber=9632794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T19:57:45Z","timestamp":1659470265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9632794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/waspaa52581.2021.9632794","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}