{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T07:23:07Z","timestamp":1751095387074,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1109\/apsipa.2016.7820732","type":"proceedings-article","created":{"date-parts":[[2017,1,19]],"date-time":"2017-01-19T21:38:58Z","timestamp":1484861938000},"page":"1-6","source":"Crossref","is-referenced-by-count":21,"title":["Audio-visual speech enhancement using deep neural networks"],"prefix":"10.1109","author":[{"given":"Jen-Cheng","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Syu-Siang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying-Hui","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Chun","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsiu-Wen","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"363","article-title":"The Hearing-Aid Speech Quality Index (HASQI)","volume":"58","author":"kates","year":"0","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638354"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref32","first-page":"885","article-title":"Ensemble modeling of denoising autoencoder for speech spectrum restoration","author":"lu","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref31","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415289"},{"key":"ref37","first-page":"1274","article-title":"Dynamic Bayesian Networks for Audio-Visual Speech Recognition","volume":"2002","author":"nefian","year":"2002","journal-title":"EURASIP Journal on Applied Signal Processing"},{"key":"ref36","first-page":"117","article-title":"Audiovisual Speech Recognition with Missing or Unreliable Data","author":"kolossa","year":"2009","journal-title":"Proc AVSP"},{"key":"ref35","article-title":"Recent Advances in the Automatic Recognition of Audio-Visual Speech","volume":"91","author":"potamianos","year":"2003","journal-title":"Proceedings of IEEE"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-13015-5"},{"journal-title":"Fundamentals of Noise Reduction in Spring Handbook of Speech Processing Chapter 43","year":"2008","author":"chen","key":"ref10"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.06.002"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851927"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref15","article-title":"Generalized maximum a posteriori spectral amplitude estimation for speech enhancement","volume":"76","author":"tsao","year":"2015","journal-title":"Speech Communication"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/89.902276"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TSA.2003.814458","article-title":"A generalized subspace approach for enhancing speech corrupted by colored noise","volume":"11","author":"hu","year":"2003","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by nonnegative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.Workshops.2007.47"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336896"},{"key":"ref3","first-page":"3002","article-title":"An investigation of spectral restoration algorithms for deep neural networks based noise robust speech recognition","author":"li","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.3571422"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-211"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607754"},{"key":"ref8","article-title":"Compression for Clinicians, Chapter 7","author":"venema","year":"2006","journal-title":"Thomson Delmar Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.04.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1002\/9781118392683"},{"key":"ref9","first-page":"111","article-title":"Noise reduction in hearing aids: an overview","volume":"38","author":"levitt","year":"2001","journal-title":"J Rehab Res Dev"},{"journal-title":"Robust Automatic Speech Recognition A Bridge to Practical Applications","year":"2015","author":"li","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2502141"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2015.7415295"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1218","DOI":"10.1109\/TSA.2005.860851","article-title":"New insights into the noise reduction Wiener filter","volume":"14","author":"chen","year":"2006","journal-title":"IEEE\/ACM Transactions on Audio Speech and Language Processing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.239"},{"key":"ref26","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","volume":"9237","author":"weninger","year":"2015","journal-title":"Latent Variable Analysis and Signal Separation"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"ref25","first-page":"2685","article-title":"Experiments on deep learning for speech denoising","author":"liu","year":"2014","journal-title":"Proc INTERSPEECH"}],"event":{"name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","start":{"date-parts":[[2016,12,13]]},"location":"Jeju, South Korea","end":{"date-parts":[[2016,12,16]]}},"container-title":["2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7803478\/7820670\/07820732.pdf?arnumber=7820732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T15:47:40Z","timestamp":1568735260000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7820732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2016.7820732","relation":{},"subject":[],"published":{"date-parts":[[2016,12]]}}}