{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:41:17Z","timestamp":1772113277917,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053214","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"181-185","source":"Crossref","is-referenced-by-count":93,"title":["Speech Enhancement Using Self-Adaptation and Multi-Head Self-Attention"],"prefix":"10.1109","author":[{"given":"Yuma","family":"Koizumi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Yatabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshiki","family":"Masuyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daiki","family":"Takeuchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Subjective test methodology for evaluating speech communication systems that include noise suppression algorithm","year":"2003","journal-title":"ITU-T Recommendation P 835"},{"key":"ref32","year":"0"},{"key":"ref31","article-title":"SDR - half-baked or well done?","author":"le roux","year":"2019","journal-title":"Proc of Int Conf on Acoust Speech and Signal Process (ICASSP)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842156"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683861"},{"key":"ref12","article-title":"MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement","author":"fu","year":"0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054578"},{"key":"ref14","article-title":"Invertible DNN-based Nonlinear Time-Frequency Transform for Speech Enhancement","author":"takeuchi","year":"2020","journal-title":"Proc of Int Conf on Acoust Speech and Signal Process (ICASSP)"},{"key":"ref15","article-title":"WaveNet: A Generative Model for Raw Audio","author":"oord","year":"2016"},{"key":"ref16","article-title":"The IBM 2015 English Conversational Telephone Speech Recognition System","author":"saon","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref17","article-title":"A Study of Speaker Adaptation for DNN-based Speech Synthesis","author":"wu","year":"2015","journal-title":"Proc of Interspeech"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-506"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2017EDP7165"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech Enhancement Generative Adversarial Network","author":"pascual","year":"2017","journal-title":"Proc of Interspeech"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952122"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex Ratio Masking for Monaural Speech Separation","author":"williamson","year":"2016","journal-title":"IEEE\/ACM Trans on Audio Speech and Lang Process"},{"key":"ref29","article-title":"Instance Normalization: The Missing Ingredient for Fast Stylization","author":"ulyanov","year":"2016"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2441"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2017.2726762","article-title":"Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks","author":"kolbak","year":"2017","journal-title":"IEEE\/ACM Trans on Audio Speech and Lang Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref26","article-title":"Attention Is All You Need","author":"vaswani","year":"2017","journal-title":"Proc 31st Conf on Neural Info Process Systems (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461778"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053214.pdf?arnumber=9053214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:03Z","timestamp":1656375063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053214","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}