{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:11:26Z","timestamp":1776885086791,"version":"3.51.2"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650194","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["Complex Recurrent Variational Autoencoder for Speech Resynthesis and Enhancement"],"prefix":"10.1109","author":[{"given":"Yuying","family":"Xie","sequence":"first","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Arildsen","sequence":"additional","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[{"name":"Aalborg University,Department of Electronic Systems,Aalborg,Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-33457-6"},{"key":"ref2","article-title":"Deep complex networks","volume-title":"ICLR","author":"Trabelsi"},{"key":"ref3","article-title":"Complex gated recurrent neural networks","volume-title":"NeurIPS","author":"Wolter"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2877909"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.12.003"},{"key":"ref7","article-title":"Phase-controlled sound transfer based on maximally-inconsistent spectrograms","volume-title":"Proceedings of the Acoustical Society of Japan Spring Meeting","author":"Roux"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9781119238805"},{"issue":"1","key":"ref10","first-page":"63","article-title":"Phase-aware speech enhancement based on deep neural networks","volume":"27","author":"Zheng","year":"2018","journal-title":"IEEE\/ACM TASLP"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682797"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682169"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref17","article-title":"Phase-aware speech enhancement with deep complex u-net","volume-title":"ICLR","author":"Choi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746374"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP52935.2021.9522648"},{"key":"ref22","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref23","article-title":"Unsupervised learning of disentangled and interpretable representations from sequential data","volume":"30","author":"Hsu","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596320"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"ref26","article-title":"A recurrent latent variable model for sequential data","volume":"28","author":"Chung","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-256"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3207349"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SSP53291.2023.10207969"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1964"},{"key":"ref31","article-title":"Unitary evolution recurrent neural networks","volume-title":"ICML","author":"Arjovsky"},{"key":"ref32","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"AISTATS","author":"Glorot"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616154"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746374"},{"key":"ref35","author":"Yamagishi","year":"2019","journal-title":"CSTR VCTK Corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref39","article-title":"SDR\u2013half-baked or well done?","volume-title":"ICASSP","author":"Le Roux"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref41","first-page":"27403","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume-title":"NASA STI\/Recon technical report n","volume":"93","author":"Garofolo","year":"1993"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846281"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650194.pdf?arnumber=10650194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:03:24Z","timestamp":1725944604000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650194","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}