{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:16:52Z","timestamp":1784301412988,"version":"3.55.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/icassp.2018.8461530","type":"proceedings-article","created":{"date-parts":[[2018,9,21]],"date-time":"2018-09-21T22:24:48Z","timestamp":1537568688000},"page":"716-720","source":"Crossref","is-referenced-by-count":100,"title":["Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization"],"prefix":"10.1109","author":[{"given":"Yoshiaki","family":"Bando","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masato","family":"Mimura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katsutoshi","family":"Itoyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031510"},{"key":"ref31","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","author":"chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref30","author":"garofalo","year":"2007","journal-title":"CSR-I (WSJ0) Complete"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74494-8_52"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2427520"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref13","first-page":"4403","article-title":"Noise reduction based on robust principal component analysis","volume":"10","author":"sun","year":"2014","journal-title":"Journal of Computational Information Systems"},{"key":"ref14","first-page":"57","article-title":"Singing-voice separation from monaural recordings using robust principal component analysis","author":"huang","year":"2012","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref15","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","author":"kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref17","author":"fabius","year":"2014","journal-title":"Variational recurrent auto-encoders"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1273","DOI":"10.21437\/Interspeech.2017-349","article-title":"Learning latent representations for speech generation and transformation","author":"hsu","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1183"},{"key":"ref28","first-page":"504","article-title":"The third CHiME speech separation and recognition challenge: Dataset, task and baselines","author":"barker","year":"2015","journal-title":"IEEE Workshop on Automatic Speech Recognition and Understanding"},{"key":"ref4","first-page":"7092","article-title":"Ideal ratio mask estimation using deep neural networks for robust speech recognition","author":"narayanan","year":"2013","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref27","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580946"},{"key":"ref6","first-page":"71","article-title":"Recurrent deep stacking networks for supervised speech separation","author":"wang","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref5","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1109\/TASSP.1984.1164453","article-title":"Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator","volume":"32","author":"ephraim","year":"1984","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref9","first-page":"546","article-title":"A statistical approach to semi-supervised speech enhancement with low-order non-negative matrix factorization","author":"mohammed","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref1","first-page":"436","article-title":"Speech enhancement based on deep denoising autoencoder","author":"lu","year":"2013","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2354456"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"2013","DOI":"10.21437\/Interspeech.2017-1672","article-title":"Speech enhancement using bayesian wavenet","author":"qian","year":"2017","journal-title":"InterSpeech"},{"key":"ref21","first-page":"499","article-title":"Combining non-negative matrix factorization and deep neural networks for speech enhancement and automatic speech recognition","author":"vu","year":"2016","journal-title":"IEEE Int Conf Acoustics Speech Signal Process"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2498101"},{"key":"ref23","first-page":"3734","article-title":"Deep neural networks for single channel source separation","author":"grais","year":"2014","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/785152"},{"key":"ref25","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"}],"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\/08461530.pdf?arnumber=8461530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T22:59:13Z","timestamp":1598223553000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8461530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp.2018.8461530","relation":{},"subject":[],"published":{"date-parts":[[2018,4]]}}}