{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:35:54Z","timestamp":1784820954288,"version":"3.55.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8462068","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"5039-5043","source":"Crossref","is-referenced-by-count":138,"title":["Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network"],"prefix":"10.1109","author":[{"given":"Meet H.","family":"Soni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep neural networks for single channel source separation","author":"grais","year":"2014","journal-title":"Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref11","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref12","author":"radford","year":"2015","journal-title":"Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR"},{"key":"ref13","author":"isola","year":"2016","journal-title":"Image-to-image translation with conditional adversarial networks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.21437\/Interspeech.2017-970","article-title":"Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks","author":"kaneko","year":"2017","journal-title":"InterSpeech"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"3364","DOI":"10.21437\/Interspeech.2017-63","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.21437\/Interspeech.2017-1620","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017","journal-title":"InterSpeech"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.21437\/Interspeech.2017-1428","article-title":"Segan: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.21437\/Interspeech.2017-962","article-title":"Generative adversarial network-based postfilter for stft spectrograms","author":"kaneko","year":"2017","journal-title":"InterSpeech"},{"key":"ref4","first-page":"6127","article-title":"A structure-preserving training target for supervised speech separation","author":"wang","year":"2014","journal-title":"Proc Int Conf Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref27","first-page":"4214","article-title":"A short-time objective intelligibility measure for time-frequency weighted noisy speech","author":"taal","year":"2010","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1852873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1007\/978-3-642-55016-4_12","article-title":"On the ideal ratio mask as the goal of computational auditory scene analysis","author":"hummersone","year":"2014","journal-title":"Blind Source Separation"},{"key":"ref7","first-page":"7092","article-title":"Ideal ratio mask estimation using deep neural networks for robust speech recognition","author":"narayanan","year":"2013","journal-title":"Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR","author":"weninger","year":"2015","journal-title":"International Conference on Latent Variable Analysis and Signal Separation (LVA\/ICA)"},{"key":"ref9","first-page":"4390","article-title":"A deep neural network for time-domain signal reconstruction","author":"wang","year":"2015","journal-title":"IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref24","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163086"},{"key":"ref26","article-title":"p. 862.2: Wideband extension to recommendation p. 862 for the assessment of wideband telephone networks and speech codecs","year":"2007","journal-title":"International Telecommunication Union Geneva"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"}],"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\/08462068.pdf?arnumber=8462068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:32:09Z","timestamp":1598247129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8462068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8462068","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}