{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:27:22Z","timestamp":1780763242017,"version":"3.54.1"},"reference-count":40,"publisher":"IEEE","license":[{"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.2019.8683231","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"71-75","source":"Crossref","is-referenced-by-count":61,"title":["Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective"],"prefix":"10.1109","author":[{"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Ohio State University, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref38","article-title":"TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation","author":"luo","year":"2018","journal-title":"arXiv preprint arXiv l809 07454v2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref32","first-page":"745","article-title":"Singing Voice Separation with Deep U-Net Convolutional Networks in","author":"jansson","year":"2017","journal-title":"Proceedings of ISMIR"},{"key":"ref31","article-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","author":"ronneberger","year":"2015","journal-title":"Proceedings of MICCAI"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref36","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":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6954314"},{"key":"ref40","first-page":"697","article-title":"TasNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation in","author":"luo","year":"2017","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2016.04.002"},{"key":"ref12","article-title":"Explicit Consistency Constraints for STFT Spectrograms and Their Application to Phase Reconstmction","author":"le roux","year":"2008","journal-title":"Proceedings ofSAPA"},{"key":"ref13","first-page":"708","article-title":"Phase-Sensitive and Recognition-Boosted Speech Separation using Deep Recurrent Neural Networks in","author":"erdogan","year":"2015","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2416653"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870725"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2042530"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(91)90014-A"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1223"},{"key":"ref4","first-page":"31","article-title":"Deep Clustering: Discriminative Embeddings for Segmentation and Separation in","author":"hershey","year":"2016","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing"},{"key":"ref27","author":"sarrof","year":"2018","journal-title":"Complex Neural Networks for Audio Dartmouth College"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref29","article-title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","author":"ping","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1700814"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref9","article-title":"Phase Estimation for Signal Reconstmction in Single-Channel Speech Separation in","author":"mowlaee","year":"2012","journal-title":"Proc OfInterSpeech"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref20","article-title":"Improving DNN-Based Music Source Separation using Phase Features in","author":"muth","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952241"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521313"},{"key":"ref23","article-title":"Phasebook and Friends: Leveraging Discrete Representations for Source Separation","author":"le roux","year":"2018","journal-title":"Arxiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2696307"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, UK","start":{"date-parts":[[2019,5,12]]},"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\/08683231.pdf?arnumber=8683231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:18:53Z","timestamp":1755800333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683231","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}