{"id":"https://openalex.org/W4405709447","doi":"https://doi.org/10.1109/iscslp63861.2024.10800519","title":"An Exploration on Singing MOS Prediction","display_name":"An Exploration on Singing MOS Prediction","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709447","doi":"https://doi.org/10.1109/iscslp63861.2024.10800519"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"article","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/A5113110576","display_name":"Yuxun Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxun Tang","raw_affiliation_strings":["School of Information, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101063912","display_name":"Jiatong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101671924","display_name":"Yuning Wu","orcid":"https://orcid.org/0000-0003-1715-2361"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuning Wu","raw_affiliation_strings":["School of Information, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["School of Information, Renmin University of China"],"affiliations":[{"raw_affiliation_string":"School of Information, Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113110576"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.3372,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5901457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"651","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.6517000198364258,"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":0.6517000198364258,"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/T10320","display_name":"Neural Networks and Applications","score":0.5871999859809875,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5633999705314636,"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":0.7775490283966064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6338058710098267},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.465139776468277},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1810973882675171},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06921026110649109}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7775490283966064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6338058710098267},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.465139776468277},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1810973882675171},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06921026110649109}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800519","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2403821559","https://openalex.org/W2963609956","https://openalex.org/W2972394484","https://openalex.org/W3161558238","https://openalex.org/W3198270377","https://openalex.org/W3202278141","https://openalex.org/W3207932315","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4223503417","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4296070386","https://openalex.org/W4372259881","https://openalex.org/W4391021560","https://openalex.org/W4391021629","https://openalex.org/W4395447377","https://openalex.org/W4402111669","https://openalex.org/W4402111789","https://openalex.org/W4402111799","https://openalex.org/W4402112070","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6795346631","https://openalex.org/W6853165267","https://openalex.org/W6862144568","https://openalex.org/W6869945801"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Mean":[0],"Opinion":[1],"Score":[2],"(MOS)":[3],"evaluations":[4],"are":[5],"not":[6],"widely":[7],"applicable":[8],"in":[9,45],"the":[10,21,25,34,68,74,86,117],"research":[11],"process":[12],"due":[13],"to":[14,98,116],"their":[15],"time-consuming":[16],"and":[17,55,80,107],"costly":[18],"nature.":[19],"In":[20],"field":[22],"of":[23,28,36,52,76,119],"speech,":[24],"rapid":[26],"development":[27,118],"MOS":[29,38,65,93,122,128],"prediction":[30,66,129],"techniques":[31],"has":[32],"enabled":[33],"use":[35],"pseudo":[37],"scores":[39],"for":[40,91,126,135],"evaluating":[41],"synthesized":[42],"audio.":[43],"However,":[44],"singing":[46,64,92,127],"domain,":[47],"there":[48],"remains":[49],"a":[50,132],"paucity":[51],"sufficient":[53],"datasets":[54],"relevant":[56],"research.":[57,137],"Consequently,":[58],"we":[59,84,96],"conduct":[60],"an":[61,120],"investigation":[62],"into":[63,109],"using":[67],"SingMOS":[69],"dataset.":[70],"By":[71],"systematically":[72],"examining":[73],"impact":[75],"different":[77],"loss":[78],"functions":[79],"various":[81],"SSL":[82],"models,":[83],"identify":[85],"most":[87],"effective":[88],"SSL-based":[89],"backbone":[90],"prediction.":[94],"Furthermore,":[95],"investigate":[97],"incorporate":[99],"additional":[100],"features,":[101],"such":[102],"as":[103],"pitch,":[104],"pitch":[105],"vari-ance\u2019":[106],"judge,":[108],"our":[110],"model.":[111],"This":[112],"comprehensive":[113],"exploration":[114],"leads":[115],"optimized":[121],"predictor":[123],"tailored":[124],"specifically":[125],"tasks,":[130],"providing":[131],"valuable":[133],"reference":[134],"further":[136]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-19T08:26:33.389920","created_date":"2025-10-10T00:00:00"}