{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T18:46:08Z","timestamp":1735584368590,"version":"3.28.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682797","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"905-909","source":"Crossref","is-referenced-by-count":10,"title":["A Deep Generative Model of Speech Complex Spectrograms"],"prefix":"10.1109","author":[{"given":"Aditya Arie","family":"Nugraha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kouhei","family":"Sekiguchi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuyoshi","family":"Yoshii","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_5"},{"key":"ref38","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"year":"2001","key":"ref32","article-title":"P.862: 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":"2003","key":"ref31","article-title":"P.862.1: Mapping function for transforming P.862 raw result scores to MOS-LQO"},{"article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","year":"2018","author":"bai","key":"ref30"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"rumelhart","year":"1986","journal-title":"Nature"},{"journal-title":"CSR-I (WSJO) Complete LDC93S6A DVD","year":"2007","author":"garofalo","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.11.005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521323"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521313"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1773"},{"key":"ref13","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref14","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref15","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"rezende","year":"2015","journal-title":"Proc ICML"},{"article-title":"WaveNet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref16"},{"article-title":"Semi-blind source separation with multichannel variational autoencoder","year":"2018","author":"kameoka","key":"ref17"},{"article-title":"Generalized multichannel variational autoencoder for underdetermined source separation","year":"2018","author":"seki","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461530"},{"key":"ref28","first-page":"933","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1977.1162950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.04.002"},{"key":"ref29","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Proc NIPS"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref8","article-title":"Explicit consistency constraints for stft spectrograms and their application to phase reconstruction","author":"le roux","year":"2008","journal-title":"Proc SAPA"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11130-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2811540"},{"journal-title":"Discrete-Time Signal Processing","year":"2009","author":"oppenheim","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659591"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.135376"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2336615"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.156"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682797.pdf?arnumber=8682797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:21:44Z","timestamp":1657855304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682797\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682797","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}