{"id":"https://openalex.org/W4416901552","doi":"https://doi.org/10.1186/s13636-025-00436-z","title":"AudioSet-tools: a Python framework for taxonomy-aware AudioSet curation and reproducible audio research","display_name":"AudioSet-tools: a Python framework for taxonomy-aware AudioSet curation and reproducible audio research","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416901552","doi":"https://doi.org/10.1186/s13636-025-00436-z"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00436-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00436-z","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13636-025-00436-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118614041","display_name":"Stefano Giacomelli","orcid":"https://orcid.org/0009-0009-0438-1748"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Stefano Giacomelli","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy"],"raw_orcid":"https://orcid.org/0009-0009-0438-1748","affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]},{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025654828","display_name":"Marco Giordano","orcid":"https://orcid.org/0009-0001-1649-6085"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Giordano","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]},{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008557705","display_name":"Claudia Rinaldi","orcid":"https://orcid.org/0000-0002-1356-8151"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudia Rinaldi","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","National Inter-University Consortium for Telecommunications (CNIT), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]},{"raw_affiliation_string":"National Inter-University Consortium for Telecommunications (CNIT), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]},{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045356859","display_name":"Fabio Graziosi","orcid":"https://orcid.org/0000-0001-7808-0707"},"institutions":[{"id":"https://openalex.org/I26415053","display_name":"University of L'Aquila","ror":"https://ror.org/01j9p1r26","country_code":"IT","type":"education","lineage":["https://openalex.org/I26415053"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Graziosi","raw_affiliation_strings":["Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L\u2019Aquila (UnivAQ), Via Vetoio, L\u2019Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]},{"raw_affiliation_string":"Department of Information Engineering, Computer Science and Mathematics (DISIM), University of L'Aquila (UnivAQ), Via Vetoio, L'Aquila, 67100, Abruzzo, Italy","institution_ids":["https://openalex.org/I26415053"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5118614041"],"corresponding_institution_ids":["https://openalex.org/I26415053"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.4624,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.90827889,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"2026","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7849000096321106,"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":0.7849000096321106,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.017799999564886093,"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/T13996","display_name":"Diverse Musicological Studies","score":0.009499999694526196,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7980999946594238},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6841999888420105},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.41769999265670776},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.40070000290870667},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.37400001287460327},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.3490000069141388},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.32899999618530273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9225000143051147},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7980999946594238},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6841999888420105},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C145644426","wikidata":"https://www.wikidata.org/wiki/Q169411","display_name":"Unified Modeling Language","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C2780154274","wikidata":"https://www.wikidata.org/wiki/Q7126717","display_name":"Download","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00436-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00436-z","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2f736c56020e47e3bb30bd1860a8c736","is_oa":true,"landing_page_url":"https://doaj.org/article/2f736c56020e47e3bb30bd1860a8c736","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2026, Iss 1, Pp 1-29 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00436-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00436-z","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2309189658","https://openalex.org/W2593116425","https://openalex.org/W2753587371","https://openalex.org/W2765407302","https://openalex.org/W2897451716","https://openalex.org/W2936774411","https://openalex.org/W2951942899","https://openalex.org/W3005033663","https://openalex.org/W3005225358","https://openalex.org/W3012504141","https://openalex.org/W3015371781","https://openalex.org/W3020588108","https://openalex.org/W3035965352","https://openalex.org/W3085893206","https://openalex.org/W3094550259","https://openalex.org/W3162999565","https://openalex.org/W3178592608","https://openalex.org/W3197097128","https://openalex.org/W3205475937","https://openalex.org/W4200337780","https://openalex.org/W4224919395","https://openalex.org/W4256604311","https://openalex.org/W4282831178","https://openalex.org/W4285483774","https://openalex.org/W4287654317","https://openalex.org/W4289915738","https://openalex.org/W4290709727","https://openalex.org/W4295312788","https://openalex.org/W4297623726","https://openalex.org/W4301395282","https://openalex.org/W4320016145","https://openalex.org/W4372260058","https://openalex.org/W4378942677","https://openalex.org/W4385823389","https://openalex.org/W4386768019","https://openalex.org/W4387244556","https://openalex.org/W4387496790","https://openalex.org/W4388032355","https://openalex.org/W4388550154","https://openalex.org/W4392672392","https://openalex.org/W4392903972","https://openalex.org/W4393753303","https://openalex.org/W4399778641","https://openalex.org/W4402712714","https://openalex.org/W4403183394","https://openalex.org/W4403661938","https://openalex.org/W4403937757","https://openalex.org/W4416515991","https://openalex.org/W6912515347","https://openalex.org/W6944207714","https://openalex.org/W6958583565"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"AudioSet-Tools,":[3],"a":[4,34,93,103],"modular":[5],"and":[6,33,55,67,71,78,106,114,138,145,149],"extensible":[7],"Python":[8],"framework":[9,60],"designed":[10],"to":[11],"streamline":[12],"the":[13,118],"creation":[14],"of":[15,81,128],"task-specific":[16],"datasets":[17,139],"derived":[18],"from":[19,28],"Google":[20],"AudioSet.":[21],"Despite":[22],"its":[23,40,89],"extensive":[24,125],"coverage,":[25],"AudioSet":[26,119],"suffers":[27],"weak":[29],"labeling,":[30],"class":[31,56],"imbalance,":[32],"loosely":[35],"structured":[36],"taxonomy,":[37],"which":[38],"hinder":[39],"applicability":[41],"in":[42,117,151],"machine":[43],"listening":[44],"workflows.":[45],"AudioSet-Tools":[46],"addresses":[47],"these":[48],"issues":[49],"through":[50,91],"configurable":[51],"taxonomy-consistent":[52],"label":[53],"filtering":[54],"rebalancing":[57],"strategies.":[58],"The":[59],"includes":[61],"automated":[62],"routines":[63],"for":[64,76],"data":[65],"download":[66],"transformation,":[68],"enabling":[69],"reproducible":[70],"semantically":[72],"consistent":[73],"dataset":[74],"generation":[75],"pre-training":[77],"downstream":[79],"fine-tuning":[80],"deep":[82],"learning":[83],"models.":[84],"While":[85],"domain-agnostic,":[86],"we":[87],"showcase":[88],"versatility":[90],"AudioSet-EV,":[92],"curated":[94],"subset":[95],"focused":[96],"on":[97,143],"emergency":[98,132],"vehicle":[99,133],"siren":[100],"recognition":[101],"\u2014":[102],"socially":[104],"relevant":[105],"technically":[107],"challenging":[108],"use":[109],"case":[110],"that":[111],"highlights":[112],"structural":[113],"semantic":[115],"gaps":[116],"taxonomy.":[120],"We":[121],"further":[122],"provide":[123],"an":[124],"comparative":[126],"benchmark":[127],"AudioSet-EV":[129],"against":[130],"state-of-the-art":[131],"corpora.":[134],"All":[135],"source":[136],"code":[137],"are":[140],"openly":[141],"released":[142],"GitHub":[144],"Zenodo,":[146],"fostering":[147],"transparency":[148],"reproducibility":[150],"real-world":[152],"audio":[153],"signal":[154],"processing":[155],"research.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-12-02T00:00:00"}
