{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:00:50Z","timestamp":1776956450697,"version":"3.51.4"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659692","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T23:11:49Z","timestamp":1552950709000},"page":"1246-1251","source":"Crossref","is-referenced-by-count":30,"title":["Time-Frequency Mask-based Speech Enhancement using Convolutional Generative Adversarial Network"],"prefix":"10.23919","author":[{"given":"Neil","family":"Shah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meet H.","family":"Soni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"IEEE ICLR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.4806631"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref35","year":"2007","journal-title":"Wideband extension to recommendation P 862 for assessment of wideband telephone networks and speech codecs"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854777"},{"key":"ref12","volume":"247","author":"bourlard","year":"2012","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref13","first-page":"2802","article-title":"Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections","author":"mao","year":"2016","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref15","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.21437\/Interspeech.2017-1465","article-title":"A fully convolutional neural network for speech enhancement","author":"park","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref19","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"186","DOI":"10.21437\/Interspeech.2017-78","article-title":"Speech enhancement based on harmonic estimation combined with MMSE to improve speech intelligibility for cochlear implant recipients","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref3","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":"ref6","first-page":"197","article-title":"All-pole modeling of degraded speech","volume":"26","author":"lim","year":"1978","journal-title":"IEEE\/ACM TASLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref8","first-page":"1849","article-title":"On training targets for supervised speech separation","volume":"22","author":"wang","year":"2014","journal-title":"IEEE\/ACM TASLP"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"3632","DOI":"10.21437\/Interspeech.2017-515","article-title":"Improving mask learning based speech enhancement system with restoration layers and residual connection","author":"chen","year":"2017","journal-title":"InterSpeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2305833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref20","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref21","first-page":"3642","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017","journal-title":"InterSpeech"},{"key":"ref24","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":"ref23","first-page":"3389","article-title":"Generative adversarial network-based postfilter for STFT spectrograms","author":"kaneko","year":"2017","journal-title":"INTER-SPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178800"},{"key":"ref25","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"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","location":"Honolulu, HI, USA","start":{"date-parts":[[2018,11,12]]},"end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659692.pdf?arnumber=8659692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T01:15:22Z","timestamp":1598231722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":36,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659692","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}