{"id":"https://openalex.org/W7107862394","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249121","title":"Human-CLAP: Human-perception-based Contrastive Language-audio Pretraining","display_name":"Human-CLAP: Human-perception-based Contrastive Language-audio Pretraining","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7107862394","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249121"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":null,"display_name":"Taisei Takano","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taisei Takano","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuki Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Okamoto","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yusuke Kanamori","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kanamori","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuki Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ryotaro Nagase","orcid":null},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryotaro Nagase","raw_affiliation_strings":["Ritsumeikan University,Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hiroshi Saruwatari","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":6.5456,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96836399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.436599999666214,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.436599999666214,"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/T10860","display_name":"Speech and Audio Processing","score":0.17419999837875366,"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":0.16920000314712524,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5935999751091003},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5573999881744385},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.48399999737739563},{"id":"https://openalex.org/keywords/rank-correlation","display_name":"Rank correlation","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5935999751091003},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5573999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338000059127808},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40400001406669617},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.40290001034736633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C101601086","wikidata":"https://www.wikidata.org/wiki/Q3753228","display_name":"Rank correlation","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.287200003862381},{"id":"https://openalex.org/C3018395757","wikidata":"https://www.wikidata.org/wiki/Q1379672","display_name":"Evaluation methods","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.271699994802475}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7071318626403809,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6076787156","display_name":null,"funder_award_id":"24K23880,25K21221","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8444121624","display_name":null,"funder_award_id":"JPMJMS2237","funder_id":"https://openalex.org/F4320320907","funder_display_name":"Japan Science and Technology Corporation"}],"funders":[{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2964213897","https://openalex.org/W2965373594","https://openalex.org/W2972394484","https://openalex.org/W3153469116","https://openalex.org/W4224871700","https://openalex.org/W4226442948","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4387969125","https://openalex.org/W4396877837","https://openalex.org/W4403674737","https://openalex.org/W4403780831","https://openalex.org/W4404317174","https://openalex.org/W4406461865","https://openalex.org/W4415433102"],"related_works":[],"abstract_inverted_index":{"Contrastive":[0],"language-audio":[1,78],"pretraining":[2],"(CLAP)":[3],"is":[4,50],"widely":[5],"used":[6],"for":[7,28],"audio":[8,35],"generation":[9],"and":[10,36,45,104],"recognition":[11],"tasks.":[12],"For":[13],"example,":[14],"CLAPScore,":[15],"which":[16],"utilizes":[17],"the":[18,29,32,41,81,88,95,102,105,115],"similarity":[19],"of":[20,31],"CLAP":[21,71],"embeddings,":[22],"has":[23,57],"been":[24],"a":[25,58,69,76],"major":[26],"metric":[27],"evaluation":[30,48,64,83,107],"relevance":[33],"between":[34,43,101],"text":[37],"in":[38],"text-to-audio.":[39],"However,":[40],"relationship":[42],"CLAPScore":[44,56,103],"human":[46,62],"subjective":[47,63,82,106],"scores":[49,108],"still":[51],"unclarified.":[52],"We":[53],"show":[54],"that":[55,91],"low":[59],"correlation":[60,98],"with":[61,114],"scores.":[65],"Additionally,":[66],"we":[67],"propose":[68],"human-perception-based":[70],"called":[72],"Human-CLAP":[73,93],"by":[74,109],"training":[75],"contrastive":[77],"model":[79],"using":[80],"score.":[84],"In":[85],"our":[86,92],"experiments,":[87],"results":[89],"indicate":[90],"improved":[94],"Spearman's":[96],"rank":[97],"coefficient":[99],"(SRCC)":[100],"more":[110],"than":[111],"0.17":[112],"compared":[113],"conventional":[116],"CLAP.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-11-28T00:00:00"}