{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:00:34Z","timestamp":1783612834584,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000055","name":"National Institute on Deafness and Other Communication Disorders","doi-asserted-by":"publisher","award":["R01 DC012048"],"award-info":[{"award-number":["R01 DC012048"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","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":[[2021]]},"DOI":"10.1109\/taslp.2021.3054302","type":"journal-article","created":{"date-parts":[[2021,1,25]],"date-time":"2021-01-25T22:51:23Z","timestamp":1611615083000},"page":"2058-2066","source":"Crossref","is-referenced-by-count":53,"title":["Towards Robust Speech Super-Resolution"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3057-9060","authenticated-orcid":false,"given":"Heming","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-6319","authenticated-orcid":false,"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3016487"},{"key":"ref38","article-title":"Dense CNN with self-attention for time-domain speech enhancement","author":"pandey","year":"2020"},{"key":"ref33","first-page":"1188r","article-title":"Memory-based approximation of the Gaussian mixture model framework for bandwidth extension of narrowband speech","author":"nour-eldin","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref32","first-page":"2494","article-title":"A mel-cepstral analysis technique restoring high frequency components from low-sampling-rate speech","author":"nakamura","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref31","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"mehri","year":"2016"},{"key":"ref30","author":"mathews","year":"2004","journal-title":"Numerical Methods Using MATLAB"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913512"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref35","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00003","article-title":"Deconvolution and checkerboard artifacts","author":"odena","year":"2016"},{"key":"ref28","first-page":"2598","article-title":"A novel method of artificial bandwidth extension using deep architecture","author":"liu","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2359987"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1979.1170672"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462362"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761236"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref22","first-page":"1270","article-title":"Audio super-resolution using neural nets","author":"kuleshov","year":"0","journal-title":"Proc Workshop Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885934"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462588"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178801"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2798811"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462049"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053712"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706637"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2909077"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/0717021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref12","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"NASA STI"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162849"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-336"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-678"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937169"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682760"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","first-page":"225","article-title":"IEEE recommended practice for speech quality measurements","volume":"17","year":"1969","journal-title":"IEEE"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6953304"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCS.2016.7843305"},{"key":"ref6","first-page":"1576","article-title":"Frequency extension of telephone narrowband speech signal using neural networks","author":"botinhao","year":"0","journal-title":"Proc Comput Eng Syst Appl"},{"key":"ref5","first-page":"765","article-title":"Perceptual evaluation of speech quality (PESQ) the new ITU standard for end-to-end speech quality assessment part II: Psychoacoustic model","volume":"50","author":"beerends","year":"2002","journal-title":"J Audio Eng Soc"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940919"},{"key":"ref7","first-page":"1178","article-title":"Bandwidth enhancement of narrowband speech signals","author":"carl","year":"0","journal-title":"Proc EUSIPCO"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref46","first-page":"2588","article-title":"Synchronous overlap and add of spectra for enhancement of excitation in artificial bandwidth extension of speech","author":"turan","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref45","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","volume":"31","author":"szegedy","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref48","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"veaux","year":"2017","journal-title":"Centre Speech Technol Res Edinburgh U K"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472814"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2118206"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref43","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1109\/JRPROC.1949.232969","article-title":"Communication in the presence of noise","volume":"37","author":"shannon","year":"0","journal-title":"Proc IRE"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09335252.pdf?arnumber=9335252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:59Z","timestamp":1652194439000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9335252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3054302","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}