{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:07:51Z","timestamp":1790269671256,"version":"4.1.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3732671","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T19:03:07Z","timestamp":1789066987000},"page":"142686-142704","source":"Crossref","is-referenced-by-count":0,"title":["Source-Aware Evaluation of SVQTD-Defined Singing Attributes: Held-Aria Transfer, Imbalance Tradeoffs, and Acoustic Evidence"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5788-6444","authenticated-orcid":false,"given":"Kehang","family":"Li","sequence":"first","affiliation":[{"name":"Xiamen University","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihong","family":"Zuo","sequence":"additional","affiliation":[{"name":"Xiamen University","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3216-3029","authenticated-orcid":false,"given":"Yuheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University","place":["Xiamen, Fujian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00240-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190732"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2011.2174224"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637747"},{"key":"ref5","first-page":"908","article-title":"Score-informed networks for music performance assessment","volume-title":"Proc. Int. Soc. Music Inf. Retr. Conf. (ISMIR)","author":"Huang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168132"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-474"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966037"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2947737"},{"key":"ref10","first-page":"825","article-title":"Learn by referencing: Towards deep metric learning for singing assessment","volume-title":"Proc. Int. Soc. Music Inf. Retr. Conf. (ISMIR)","author":"Zhang"},{"key":"ref11","first-page":"904","article-title":"Training explainable singing quality assessment network with augmented data","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096309"},{"key":"ref13","first-page":"468","article-title":"VocalSet: A singing voice dataset","volume-title":"Proc. 19th Int. Soc. Music Inf. Retr. Conf. (ISMIR)","author":"Wilkins"},{"key":"ref14","first-page":"890","article-title":"Investigating time-frequency representations for audio feature extraction in singing technique classification","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Yamamoto"},{"key":"ref15","first-page":"1","article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","volume-title":"Proc. 12th Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3602320"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2022.3188113"},{"key":"ref18","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0377-82"},{"key":"ref20","volume-title":"The Science of the Singing Voice","author":"Sundberg","year":"1987"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.424266"},{"key":"ref22","article-title":"Vibrato","volume-title":"Voice Quality Measurement","author":"Hirano","year":"1995"},{"key":"ref23","volume-title":"The Diagnosis and Correction of Vocal Faults","author":"McKinney","year":"1994"},{"key":"ref24","volume-title":"PRAAT: Doing Phonetics by Computer","author":"Boersma","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref29","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn. (ICML)","volume":"70","author":"Guo"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1111\/ecog.02881"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.06.061"},{"key":"ref32","first-page":"1","article-title":"A study on the possibility of artificial intelligence empowering vocal courses in comprehensive universities under the background of educational digitalization strategy","author":"Zhang","year":"2025","journal-title":"China Music J. Netw."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref34","first-page":"4175","article-title":"Balanced meta-softmax for long-tailed visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ren"},{"key":"ref35","first-page":"1","article-title":"Long-tail learning via logit adjustment","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Menon"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/4615733"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3758148"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0034"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11686001.pdf?arnumber=11686001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T16:44:45Z","timestamp":1790268285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11686001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3732671","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}