{"id":"https://openalex.org/W4406461520","doi":"https://doi.org/10.1109/slt61566.2024.10832260","title":"Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion","display_name":"Pitch-and-Spectrum-Aware Singing Quality Assessment with Bias Correction and Model Fusion","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461520","doi":"https://doi.org/10.1109/slt61566.2024.10832260"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089019283","display_name":"Yufei Shi","orcid":"https://orcid.org/0000-0002-6999-0191"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Fei Shi","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072371384","display_name":"Ye-Xin Lu","orcid":"https://orcid.org/0009-0009-8026-0702"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye-Xin Lu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067982618","display_name":"Hui-Peng Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui-Peng Du","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069176378","display_name":"Zhen-Hua Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Research Center of Speech and Language Information Processing,Hefei,P. R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"811","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8024637699127197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6808568239212036},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6022749543190002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5697872042655945},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5188047289848328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3644077181816101},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19769224524497986},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07550081610679626}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8024637699127197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808568239212036},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6022749543190002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5697872042655945},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5188047289848328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3644077181816101},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19769224524497986},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07550081610679626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W70888257","https://openalex.org/W1607425652","https://openalex.org/W2557915412","https://openalex.org/W2786387703","https://openalex.org/W2921893894","https://openalex.org/W2933138175","https://openalex.org/W2963403924","https://openalex.org/W2972394484","https://openalex.org/W2998572311","https://openalex.org/W3097777922","https://openalex.org/W3202278141","https://openalex.org/W3215615641","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4297841508","https://openalex.org/W4307323391","https://openalex.org/W4311167834","https://openalex.org/W4372260498","https://openalex.org/W4372348289","https://openalex.org/W4391021560","https://openalex.org/W4391021629","https://openalex.org/W4399875170","https://openalex.org/W6729924827","https://openalex.org/W6772349387","https://openalex.org/W6791252611","https://openalex.org/W6793309411","https://openalex.org/W6809935456"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"We":[0],"participated":[1],"in":[2],"track":[3],"2":[4],"of":[5,19],"the":[6,14,25,33,60,83],"VoiceMOS":[7],"Challenge":[8],"2024,":[9],"which":[10,71],"aimed":[11],"to":[12,90,104],"predict":[13],"mean":[15],"opinion":[16],"score":[17],"(MOS)":[18],"singing":[20,66],"samples.":[21],"Our":[22],"submission":[23,43],"secured":[24],"first":[26],"place":[27],"among":[28],"all":[29,118,122],"participating":[30],"teams,":[31],"excluding":[32],"official":[34],"baseline.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"further":[40,105],"improve":[41],"our":[42,113],"and":[44,68,77,99],"propose":[45],"a":[46,86],"novel":[47],"Pitch-and-Spectrum-aware":[48],"Singing":[49],"Quality":[50],"Assessment":[51],"(PS-SQA)":[52],"method.":[53],"The":[54],"PS-SQA":[55,84,115],"is":[56],"designed":[57],"based":[58],"on":[59],"self-supervised-learning":[61],"(SSL)":[62],"MOS":[63],"predictor,":[64],"incorporating":[65],"pitch":[67,75],"spectral":[69],"information,":[70],"are":[72],"extracted":[73],"using":[74],"histogram":[76],"non-quantized":[78],"neural":[79],"codec,":[80],"respectively.":[81],"Additionally,":[82],"introduces":[85],"bias":[87],"correction":[88],"strategy":[89],"address":[91],"prediction":[92,107],"biases":[93],"caused":[94],"by":[95],"low-resource":[96],"training":[97],"samples,":[98],"employs":[100],"model":[101],"fusion":[102],"technology":[103],"enhance":[106],"accuracy.":[108],"Experimental":[109],"results":[110],"confirm":[111],"that":[112],"proposed":[114],"significantly":[116],"outperforms":[117],"competing":[119],"systems":[120],"across":[121],"system-level":[123],"metrics,":[124],"confirming":[125],"its":[126],"strong":[127],"sing":[128],"quality":[129],"assessment":[130],"capabilities.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}