{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:20:22Z","timestamp":1775229622115,"version":"3.50.1"},"reference-count":60,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271314"],"award-info":[{"award-number":["62271314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2023.3271151","type":"journal-article","created":{"date-parts":[[2023,4,27]],"date-time":"2023-04-27T18:26:12Z","timestamp":1682619972000},"page":"1758-1770","source":"Crossref","is-referenced-by-count":14,"title":["Speech Enhancement With Integration of Neural Homomorphic Synthesis and Spectral Masking"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4063-8952","authenticated-orcid":false,"given":"Wenbin","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7102-9826","authenticated-orcid":false,"given":"Kai","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747647"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747230"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747888"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref52","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10411"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053296"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683130"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3188"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2991537"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref45","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","author":"recommendation","year":"2001","journal-title":"Int Telecomm Union Geneva Switzerland ITU-T Rec"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746273"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415105"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1910"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870758"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747177"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2180896"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref40","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414569"},{"key":"ref36","first-page":"3","article-title":"CBAM: Convolutional block attention module","author":"woo","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref31","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref30","year":"1979","journal-title":"IEEE Acoustics Speech and Signal Processing Society Programs for Digital Signal Processing"},{"key":"ref33","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.811544"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746171"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746610"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747578"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747521"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17710"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2537"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1482"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1405"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-24"},{"key":"ref29","author":"rabiner","year":"2010","journal-title":"Theory and Applications of Digital Speech Processing"},{"key":"ref60","first-page":"6493","article-title":"DNSMOS: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","author":"reddy","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10109754.pdf?arnumber=10109754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:22:10Z","timestamp":1686594130000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10109754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3271151","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}