{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:28:51Z","timestamp":1777984131384,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["19H04137"],"award-info":[{"award-number":["19H04137"]}]},{"name":"NII CRIS-Line Collaborative Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2020.2979603","type":"journal-article","created":{"date-parts":[[2020,3,9]],"date-time":"2020-03-09T15:44:40Z","timestamp":1583768680000},"page":"1104-1117","source":"Crossref","is-referenced-by-count":24,"title":["A Flow-Based Deep Latent Variable Model for Speech Spectrogram Modeling and Enhancement"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5424-747X","authenticated-orcid":false,"given":"Aditya Arie","family":"Nugraha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6160-9301","authenticated-orcid":false,"given":"Kouhei","family":"Sekiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8387-8609","authenticated-orcid":false,"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-73031-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659591"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683704"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2944348"},{"key":"ref8","first-page":"1","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref9","volume-title":"Monte Carlo Statistical Methods","author":"Robert","year":"2010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1063\/1.1699114"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/57.1.97"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref13","first-page":"1","article-title":"Semi-blind source separation with multichannel variational autoencoder","author":"Kameoka","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1398"},{"key":"ref15","first-page":"1","article-title":"From optimal transport to generative modeling: The VEGAN cookbook","author":"Bousquet","year":"2017"},{"key":"ref16","first-page":"1","article-title":"Wasserstein auto-encoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tolstikhin","year":"2018"},{"key":"ref17","first-page":"1","article-title":"Diagnosing and enhancing VAE models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dai","year":"2019"},{"key":"ref18","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rezende","year":"2015"},{"key":"ref19","first-page":"1","article-title":"Density estimation using Real NVP","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2017"},{"key":"ref20","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kingma","year":"2018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-5014-9_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref23","first-page":"856","article-title":"Hyperspherical variational auto-encoders","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Davidson","year":"2018"},{"key":"ref24","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"ref25","first-page":"1","article-title":"NICE: Non-linear independent components estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dinh","year":"2015"},{"key":"ref26","first-page":"4743","article-title":"Improving variational inference with inverse autoregressive flow","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Kingma","year":"2016"},{"key":"ref27","first-page":"1","article-title":"Dimensionality reduction flows","author":"Das","year":"2019"},{"key":"ref28","first-page":"1","article-title":"WaveNet: A generative model for raw audio","author":"Oord","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref30","first-page":"3370","article-title":"FloWaveNet : A generative flow for raw audio","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139626514"},{"key":"ref32","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ioffe","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974409"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2003.11.019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.9734\/BJMCS\/2015\/13026"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162950"},{"key":"ref41","first-page":"1","article-title":"On the variance of the adaptive learning rate and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu","year":"2020"},{"key":"ref42","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref43","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pascanu","year":"2013"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref45","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Snderby","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_5"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/e19020047"},{"key":"ref48","volume-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref50","article-title":"Perceptual evaluation of speech quality (PESQ): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","year":"2001"},{"key":"ref51","article-title":"Wideband extension to Recommendation P.862 for the assessment of wideband telephone networks and speech codecs","year":"2007"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521313"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553396"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682744"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74494-8_69"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1480"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682797"},{"key":"ref59","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682623"},{"key":"ref61","first-page":"1","article-title":"Hierarchical generative modeling for controllable speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hsu","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461384"},{"key":"ref63","first-page":"747","article-title":"MIDI-VAE: Modeling dynamics and instrumentation of music with applications to style transfer","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Brunner","year":"2018"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/09028147.pdf?arnumber=9028147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T19:29:02Z","timestamp":1706038142000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9028147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/taslp.2020.2979603","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.12375284.v1","asserted-by":"object"}]},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}