{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T06:55:27Z","timestamp":1777618527885,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JSPS KAKENHI","award":["21K11957"],"award-info":[{"award-number":["21K11957"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3095656","type":"journal-article","created":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T19:48:01Z","timestamp":1625773681000},"page":"2591-2605","source":"Crossref","is-referenced-by-count":4,"title":["Gamma Boltzmann Machine for Audio Modeling"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1863-6771","authenticated-orcid":false,"given":"Toru","family":"Nakashika","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1345-0663","authenticated-orcid":false,"given":"Kohei","family":"Yatabe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/rs10060878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-962"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref30","article-title":"MelNet: A generative model for audio in the frequency domain","author":"vasquez","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660842"},{"key":"ref36","first-page":"253","article-title":"Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors","volume":"1","author":"martin","year":"2002","journal-title":"Proc IEEE Int Conf Acoust Speech and Signal Process"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2004.840869"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2003.813679"},{"key":"ref10","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML’15 Proc 32nd Int Conf Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref13","first-page":"912","article-title":"Unsupervised learning of distributions of binary vectors using two layer networks","author":"freund","year":"1994"},{"key":"ref14","first-page":"873","article-title":"Sparse deep belief net model for visual area V2","author":"lee","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273596"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.gexplo.2014.02.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495651"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2607341"},{"key":"ref4","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947700"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3000593"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref29","first-page":"471","article-title":"Gamma boltzmann machine for simultaneously modeling linear- and log-amplitude spectra","author":"nakashika","year":"2020","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref5","first-page":"84","article-title":"Statistical parametric speech synthesis incorporating generative adversarial networks","volume":"26","author":"saito","year":"2017","journal-title":"IEEE Transactions on Audio"},{"key":"ref8","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"oord","year":"2016","journal-title":"Proc ICML"},{"key":"ref7","first-page":"910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"14","author":"kumar","year":"2019","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1140"},{"key":"ref9","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref1","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-717"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2414"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593263"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1109\/TASLP.2015.2512042","article-title":"Complex ratio masking for monaural speech separation","volume":"24","author":"williamson","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2516032"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486611"},{"key":"ref41","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518514"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1753"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639187"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09478208.pdf?arnumber=9478208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T20:00:24Z","timestamp":1639771224000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9478208\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3095656","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}