{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:02:41Z","timestamp":1765357361732,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Ritsumeikan Advanced Research Academy"},{"name":"Ritsumeikan Global Innovation Research Organization"},{"name":"JSPS KAKENHI","award":["JP20K19827","JP19H04142","JP21H03488","JP21H04427","JP21K18372"],"award-info":[{"award-number":["JP20K19827","JP19H04142","JP21H03488","JP21H04427","JP21K18372"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3268577","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T21:14:55Z","timestamp":1682025295000},"page":"1667-1680","source":"Crossref","is-referenced-by-count":9,"title":["Inter-Frequency Phase Difference for Phase Reconstruction Using Deep Neural Networks and Maximum Likelihood"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3883-1315","authenticated-orcid":false,"given":"Nguyen Binh","family":"Thien","sequence":"first","affiliation":[{"name":"Graduate School of Information Science and Engineering, Ritsumeikan University, Shiga, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8846-3699","authenticated-orcid":false,"given":"Yukoh","family":"Wakabayashi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Toyohashi University of Technology, Toyohashi, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9738-8579","authenticated-orcid":false,"given":"Kenta","family":"Iwai","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1706-4743","authenticated-orcid":false,"given":"Takanobu","family":"Nishiura","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Improving DNN-Based music source separation using phase features","author":"muth","year":"2018","journal-title":"Joint Workshop Mach Learn Music"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-611"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref11","first-page":"860","article-title":"Sensitivity of human hearing to changes in phase spectrum","volume":"61","author":"laitinen","year":"2013","journal-title":"J Audio Eng Soc"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108116"},{"journal-title":"Recommendation ITU-R BS 1116-3 Methods for the subjective assessment of small impairments in audio systems","year":"2015","key":"ref54"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1773"},{"key":"ref16","first-page":"497","article-title":"Multitask-based joint learning approach to robust ASR for radio communication speech","author":"ma","year":"0","journal-title":"Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2811540"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2904183"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107368"},{"article-title":"Accurate eigenvalues of a symmetric tri-diagonal matrix","year":"1966","author":"kahan","key":"ref46"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1137\/0111030"},{"key":"ref48","article-title":"TIMIT Acoustic Phonetic Continuous Speech Corpus","author":"garofolo","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0892-3"},{"key":"ref42","first-page":"375","article-title":"Signal reconstruction from STFT magnitude: A state of the art","author":"sturmel","year":"0","journal-title":"Proc Int Conf Digit Audio Effects"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683423"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898717655"},{"journal-title":"Two-Dimensional Phase Unwrapping Theory Algorithms and Software","year":"1998","author":"ghiglia","key":"ref43"},{"key":"ref49","article-title":"Wavenet: A generative model for raw audio","volume":"125","author":"oord","year":"0","journal-title":"Proc 9th ISCA Workshop Speech Synthesis Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1049\/el.2009.3328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221041"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-014-0038-1"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053234"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2369251"},{"key":"ref6","first-page":"995","article-title":"Two-stage phase reconstruction using DNN and von mises distribution-based maximum likelihood","author":"nguyen","year":"0","journal-title":"Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413722"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682797"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870742"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034486"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521313"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2678166"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC53105.2022.9914686"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876858"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/5.135376"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2479045"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2430820"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854449"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2336615"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-488"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461714"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-962"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953220"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2439038"},{"key":"ref28","first-page":"397","article-title":"Fast signal reconstruction from magnitude STFT spectrogram based on spectrogram consistency","volume":"10","author":"roux","year":"0","journal-title":"Proc Int Conf Digit Audio Effects"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362333"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2884026"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10106067.pdf?arnumber=10106067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T18:05:18Z","timestamp":1684778718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10106067\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3268577","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2023]]}}}