{"id":"https://openalex.org/W4372348289","doi":"https://doi.org/10.1109/icassp49357.2023.10096309","title":"Tg-Critic: A Timbre-Guided Model For Reference-Independent Singing Evaluation","display_name":"Tg-Critic: A Timbre-Guided Model For Reference-Independent Singing Evaluation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348289","doi":"https://doi.org/10.1109/icassp49357.2023.10096309"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.09127","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064077063","display_name":"Xiaoheng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoheng Sun","raw_affiliation_strings":["NetEase Cloud Music,Shanghai,China","NetEase Cloud Music, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Cloud Music,Shanghai,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Cloud Music, Shanghai, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088173321","display_name":"Yuejie Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuejie Gao","raw_affiliation_strings":["NetEase Cloud Music,Shanghai,China","NetEase Cloud Music, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Cloud Music,Shanghai,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Cloud Music, Shanghai, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009764500","display_name":"Hanyao Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyao Lin","raw_affiliation_strings":["Fudan University,Shanghai,China","Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["NetEase Cloud Music,Shanghai,China","NetEase Cloud Music, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Cloud Music,Shanghai,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Cloud Music, Shanghai, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9916999936103821,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.989799976348877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9477355480194092},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8984940052032471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7710080742835999},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5946565270423889},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5872132778167725},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49808669090270996},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48981377482414246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4749869406223297},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4741365611553192},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4662289619445801},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4184810519218445},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09563469886779785},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07150900363922119},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06915727257728577}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9477355480194092},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8984940052032471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710080742835999},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5946565270423889},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5872132778167725},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49808669090270996},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48981377482414246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4749869406223297},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4741365611553192},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4662289619445801},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4184810519218445},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09563469886779785},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07150900363922119},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06915727257728577},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2305.09127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.09127","pdf_url":"https://arxiv.org/pdf/2305.09127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.09127","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.09127","pdf_url":"https://arxiv.org/pdf/2305.09127","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372348289.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W75331887","https://openalex.org/W109946471","https://openalex.org/W125192980","https://openalex.org/W1500744329","https://openalex.org/W1602546179","https://openalex.org/W1973249776","https://openalex.org/W2067709094","https://openalex.org/W2089956847","https://openalex.org/W2116310157","https://openalex.org/W2133764290","https://openalex.org/W2133771225","https://openalex.org/W2187089797","https://openalex.org/W2219405113","https://openalex.org/W2340344296","https://openalex.org/W2786387703","https://openalex.org/W2890271810","https://openalex.org/W2935962565","https://openalex.org/W2954750335","https://openalex.org/W2963285578","https://openalex.org/W2981056126","https://openalex.org/W2991095666","https://openalex.org/W3014641072","https://openalex.org/W3033364247","https://openalex.org/W3131347419","https://openalex.org/W3151395980","https://openalex.org/W3215970941","https://openalex.org/W4238041734","https://openalex.org/W4245692952","https://openalex.org/W6680216143","https://openalex.org/W6685562342","https://openalex.org/W6764754933","https://openalex.org/W6791252611","https://openalex.org/W6793309411","https://openalex.org/W6804049149","https://openalex.org/W6968595903"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2406877384","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2595839522","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W4288088492","https://openalex.org/W2982290989"],"abstract_inverted_index":{"Automatic":[0],"singing":[1,23,37,51,78,116],"evaluation":[2,52,76,117],"independent":[3],"of":[4,22,36,69,77,83],"reference":[5],"melody":[6],"is":[7,61,85,109],"a":[8,28,57,88,101,113],"challenging":[9],"task":[10],"due":[11],"to":[12,45,63,73,91,111],"its":[13],"subjective":[14],"and":[15,31],"multi-dimensional":[16],"nature.":[17],"As":[18],"an":[19,105],"essential":[20],"attribute":[21],"voices,":[24],"vocal":[25],"timbre":[26,47,65],"has":[27,42],"non-negligible":[29],"effect":[30],"influence":[32],"on":[33],"human":[34],"perception":[35],"quality.":[38,79],"However,":[39],"no":[40],"research":[41],"been":[43],"done":[44],"include":[46],"information":[48,95],"explicitly":[49],"in":[50,100,135],"models.":[53],"In":[54],"this":[55],"paper,":[56],"data-driven":[58],"model":[59,71,129],"TG-Critic":[60,84],"proposed":[62,128],"introduce":[64],"embeddings":[66],"as":[67,87],"one":[68],"the":[70,75,93,127,131],"inputs":[72],"guide":[74],"The":[80,122],"trunk":[81],"structure":[82],"designed":[86,110],"multi-scale":[89],"network":[90],"summarize":[92],"contextual":[94],"from":[96],"constant-Q":[97],"transform":[98],"features":[99],"high-resolution":[102],"way.":[103],"Furthermore,":[104],"automatic":[106],"annotation":[107],"method":[108],"construct":[112],"large":[114],"three-class":[115],"dataset":[118],"with":[119],"low":[120],"human-effort.":[121],"experimental":[123],"results":[124],"show":[125],"that":[126],"outperforms":[130],"existing":[132],"state-of-the-art":[133],"models":[134],"most":[136],"cases.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}