{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:22:52Z","timestamp":1783693372045,"version":"3.55.0"},"reference-count":95,"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\/4.0\/legalcode"}],"funder":[{"name":"Shenzhen Sustainable Support Program for High-level University","award":["20200925154002001"],"award-info":[{"award-number":["20200925154002001"]}]},{"DOI":"10.13039\/501100020950","name":"National Science and Technology Council","doi-asserted-by":"publisher","award":["111-2221-E-001-016-MY3"],"award-info":[{"award-number":["111-2221-E-001-016-MY3"]}],"id":[{"id":"10.13039\/501100020950","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001869","name":"Academia Sinica","doi-asserted-by":"publisher","award":["AS-GC-111-M01"],"award-info":[{"award-number":["AS-GC-111-M01"]}],"id":[{"id":"10.13039\/501100001869","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.2022.3205757","type":"journal-article","created":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T19:43:35Z","timestamp":1664480615000},"page":"54-70","source":"Crossref","is-referenced-by-count":85,"title":["Deep Learning-Based Non-Intrusive Multi-Objective Speech Assessment Model With Cross-Domain Features"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7319-8263","authenticated-orcid":false,"given":"Ryandhimas E.","family":"Zezario","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3487-8212","authenticated-orcid":false,"given":"Szu-Wei","family":"Fu","sequence":"additional","affiliation":[{"name":"Microsoft, Vancouver, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6988-492X","authenticated-orcid":false,"given":"Fei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6174-2556","authenticated-orcid":false,"given":"Chiou-Shann","family":"Fuh","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6956-0418","authenticated-orcid":false,"given":"Yu","family":"Tsao","sequence":"additional","affiliation":[{"name":"Research Center for Information Technology Innovation, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053214"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2108"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414182"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1844"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362072"},{"key":"ref74","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/JSTSP.2019.2922820","article-title":"SpeakerBeam: Speaker aware neural network for target speaker extraction in speech mixtures","volume":"13","author":"zmolikova","year":"2019","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461827"},{"key":"ref75","article-title":"Dynamic noise embedding: Noise aware training and adaptation for speech enhancement","author":"lee","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1374"},{"key":"ref78","first-page":"899","article-title":"The design for the wall street journal-based CSR corpus","author":"paul","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref79","article-title":"PNL 100 nonspeech sounds[online]","author":"hu","year":"2010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/10.0005899"},{"key":"ref32","first-page":"366","volume":"61","author":"beerends","year":"2013","journal-title":"J Audio Eng Soc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2012.11.007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.103204"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3039929"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.09.004"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2401513"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2425"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616163"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2847459"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052949"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1121\/1.1862575"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1121\/1.426848"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1121\/1.1953107"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683770"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.05.001"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2809"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.543199"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.1916407"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081272"},{"key":"ref24","first-page":"355","article-title":"Evaluation of speech transmission channels by using artificial signals","volume":"25","author":"houtgast","year":"1971","journal-title":"Acustica"},{"key":"ref23","article-title":"Methods for calculation of the speech intelligibility index","year":"1997"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.1804628"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.384464"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3152672"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10828"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10838"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2644258"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1097\/00003446-200508000-00002"},{"key":"ref91","article-title":"Development of Taiwan mandarin hearing in noise test","author":"huang","year":"2005"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747180"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3165442"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref56","first-page":"2031","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","volume":"97","author":"fu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref53","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref10","first-page":"1","article-title":"Non-intrusive quality assessment for enhanced speech signals based on spectro temporal features","author":"li","year":"0","journal-title":"Proc IEEE Int Conf Multimedia Expo Workshops"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2015.7230477"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682754"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.04.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE.2014.6993412"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2174223"},{"key":"ref82","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-11301-7_34"},{"key":"ref81","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4304\/jmm.2.5.19-26"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-012-9162-4"},{"key":"ref83","article-title":"Darpa timit acoustic-phonetic continuous speech corpus CD-ROM TIMIT","author":"garofolo","year":"1993"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WICOM.2010.5600267"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.2307\/1412159"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref4","first-page":"626","author":"roux","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-350"},{"key":"ref6","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":"rix","year":"0","journal-title":"ITU-T Recommendation"},{"key":"ref5","first-page":"711","article-title":"Optimal scale-invariant signal-to-noise ratio and curriculum learning for monaural multi-speaker speech separation in noisy environment","author":"ma","year":"0","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10153"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032266"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/89.902276"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-45"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383533"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8281993"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.883250"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053366"},{"key":"ref45","first-page":"477","article-title":"A deep learning-based time-domain approach for non-intrusive speech quality assessment","author":"jia","year":"0","journal-title":"Proc Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref47","first-page":"482","article-title":"STOI-Net: A deep learning based non-intrusive speech intelligibility assessment model","author":"zezario","year":"0","journal-title":"Proc IEEE Asia-Pacific Signal Inf Process Assoc Annu Summit Conf"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683175"},{"key":"ref41","first-page":"85","article-title":"Intrusive and nonintrusive perceptual speech quality assessment using a convolutional neural network","author":"gamper","year":"0","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref43","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\/09905733.pdf?arnumber=9905733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:26:47Z","timestamp":1672082807000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9905733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3205757","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}