{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:48:16Z","timestamp":1776883696408,"version":"3.51.2"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832260","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"811-817","source":"Crossref","is-referenced-by-count":2,"title":["Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion"],"prefix":"10.1109","author":[{"given":"Yu-Fei","family":"Shi","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye-Xin","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui-Peng","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen-Hua","family":"Ling","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"492","article-title":"Spectral features and pitch histogram for automatic singing quality evaluation with CRNN","volume-title":"Proc. APSIPA","author":"Huang"},{"key":"ref2","first-page":"904","article-title":"Training explainable singing quality assessment network with augmented data","volume-title":"Proc. APSIPA","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2005-72"},{"key":"ref5","article-title":"AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech","author":"Patton","year":"2016","journal-title":"arXiv preprint arXiv:1611.09207"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-970"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389763"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1076\/jnmr.32.2.143.16743"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282110"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPA.2018.8659545"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref16","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205757"},{"key":"ref18","first-page":"416","article-title":"Automatic rank-ordering of singing vocals with twin-neural network","volume-title":"Proc. ISMIR","author":"Gupta"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095676"},{"key":"ref21","first-page":"5443","article-title":"Fusion of selfsupervised learned models for MOS prediction","volume-title":"Proc. Interspeech","author":"Yang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-105"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389788"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref25","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832260.pdf?arnumber=10832260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:08:19Z","timestamp":1737101299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832260","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}