{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T11:23:13Z","timestamp":1780053793147,"version":"3.54.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462040","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T18:24:48Z","timestamp":1537554288000},"page":"5059-5063","source":"Crossref","is-referenced-by-count":37,"title":["Monaural Speech Enhancement Using Deep Neural Networks by Maximizing a Short-Time Objective Intelligibility Measure"],"prefix":"10.1109","author":[{"given":"Morten","family":"Kolbaek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","author":"garofolo","year":"1993","journal-title":"DARPA TIMIT Acoustic Phonetic Continuous Speech Corpus CDROM"},{"key":"ref32","article-title":"The third ‘CHiME’ Speech Separation and Recognition Challenge: Dataset, task and baselines","author":"barker","year":"2015","journal-title":"Proc ASRU"},{"key":"ref31","author":"kolbrek","year":"0","journal-title":"Supplemental Material"},{"key":"ref30","article-title":"CSR-I (WSJ0) Complete LDC93s6a","author":"garofolo","year":"1993","journal-title":"Philadelphia Linguistic Data Consortium"},{"key":"ref36","first-page":"305","article-title":"Speech Enhancement using Long Short-Term Memory based Recurrent Neural Networks for Noise Robust Speaker Verification","author":"kolbrek","year":"2016","journal-title":"Proc SLT"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref34","year":"1993","journal-title":"Rec P 56 Objective measurement of active speech level"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.4929493"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.4984271"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref14","author":"moore","year":"2013","journal-title":"An Introduction to the Psychology of Hearing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000302"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.815936"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/89.748118"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851929"},{"key":"ref28","first-page":"504","article-title":"Matching pursuit for channel selection in cochlear implants based on an intelligibility metric","author":"taal","year":"2012","journal-title":"Proc EUSIPCO"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.2766778"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2588002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2157685"},{"key":"ref29","article-title":"An introduction to computational networks and the computational network toolkit","author":"agarwal","year":"2014","journal-title":"Microsoft Technical Report MSR-TR -2014-112 Tech Rep"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.3299168"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref7","first-page":"1","article-title":"Single channel speech music separation using nonnegative matrix factorization and spectral masks","author":"grais","year":"2011","journal-title":"Proc ICDSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2200\/S00473ED1V01Y201301SAP011"},{"key":"ref20","first-page":"5078","article-title":"SOBM - a binary mask for noisy speech that optimises an objective intelligibility metric","author":"lightburn","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1284"},{"key":"ref21","first-page":"446","article-title":"Perceptual weighting deep neural networks for single-channel speech enhancement","author":"han","year":"0","journal-title":"Proc (WCICA 2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952122"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref25","author":"goodfellow","year":"2016","journal-title":"Deep Learning"}],"event":{"name":"ICASSP 2018 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Calgary, AB","start":{"date-parts":[[2018,4,15]]},"end":{"date-parts":[[2018,4,20]]}},"container-title":["2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8450881\/8461260\/08462040.pdf?arnumber=8462040","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:28:46Z","timestamp":1598228926000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462040\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462040","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}