{"id":"https://openalex.org/W7214656282","doi":"https://doi.org/10.5281/zenodo.23010849","title":"Data and Code Release for \"Benchmarking Multilingual ASR for Tagalog and Cebuano Across Scoring Conventions and Language Coverage\" (NLPIR 2026)","display_name":"Data and Code Release for \"Benchmarking Multilingual ASR for Tagalog and Cebuano Across Scoring Conventions and Language Coverage\" (NLPIR 2026)","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214656282","doi":"https://doi.org/10.5281/zenodo.23010849"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23010849","doi":"https://doi.org/10.5281/zenodo.23010849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23010849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23010849","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153269165","display_name":"Nash Golosino","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I260054107","display_name":"University of the Immaculate Conception","ror":"https://ror.org/0204b4294","country_code":"PH","type":"education","lineage":["https://openalex.org/I260054107"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Golosino, Nash","raw_affiliation_strings":["University of the Immaculate Conception"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Immaculate Conception","institution_ids":["https://openalex.org/I260054107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153342115","display_name":"Ma. Nicole Morales","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I260054107","display_name":"University of the Immaculate Conception","ror":"https://ror.org/0204b4294","country_code":"PH","type":"education","lineage":["https://openalex.org/I260054107"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Morales, Ma. Nicole","raw_affiliation_strings":["University of the Immaculate Conception"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Immaculate Conception","institution_ids":["https://openalex.org/I260054107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021005448","display_name":"Kristine Mae M. Adlaon","orcid":"https://orcid.org/0000-0003-3020-6627","observed_orcids":["https://orcid.org/0000-0003-3020-6627"]},"institutions":[{"id":"https://openalex.org/I260054107","display_name":"University of the Immaculate Conception","ror":"https://ror.org/0204b4294","country_code":"PH","type":"education","lineage":["https://openalex.org/I260054107"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Adlaon, Kristine Mae","raw_affiliation_strings":["University of the Immaculate Conception"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of the Immaculate Conception","institution_ids":["https://openalex.org/I260054107"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I260054107"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0003000000142492354,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00019999999494757503,"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/multilingual-speech-recognition","display_name":"multilingual speech recognition","score":0.8529999852180481},{"id":"https://openalex.org/keywords/tagalog","display_name":"Tagalog","score":0.9620000123977661},{"id":"https://openalex.org/keywords/cebuano","display_name":"Cebuano","score":1.0},{"id":"https://openalex.org/keywords/whisper","display_name":"Whisper","score":0.6010000109672546},{"id":"https://openalex.org/keywords/language-coverage","display_name":"language coverage","score":0.527999997138977},{"id":"https://openalex.org/keywords/linguistic-identity","display_name":"linguistic identity","score":0.33399999141693115},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.5329999923706055},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.574999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496999740600586},{"id":"https://openalex.org/C2779388314","wikidata":"https://www.wikidata.org/wiki/Q34057","display_name":"Tagalog","level":2,"score":0.7032999992370605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5734000205993652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503000020980835},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4952999949455261},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4528999924659729},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27410000562667847}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.23010849","doi":"https://doi.org/10.5281/zenodo.23010849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23010849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.23010850","doi":"https://doi.org/10.5281/zenodo.23010850","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23010850","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.23015266","doi":"https://doi.org/10.5281/zenodo.23015266","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23015266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23010849","doi":"https://doi.org/10.5281/zenodo.23010849","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23010849","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7167823543","https://openalex.org/W7203871948","https://openalex.org/W7216939665","https://openalex.org/W7164996513","https://openalex.org/W7131785470","https://openalex.org/W7202199293","https://openalex.org/W7154280776","https://openalex.org/W7166107903","https://openalex.org/W2999395250","https://openalex.org/W7203442692"],"abstract_inverted_index":{"Release":[0],"archive":[1,148],"for":[2,10,103,149],"the":[3,25,42,49,58,64,83,93,97,104,109,115,147],"NLPIR":[4],"2026":[5],"paper":[6],"\"Benchmarking":[7],"Multilingual":[8],"ASR":[9],"Tagalog":[11],"and":[12,17,37,45,54,60,70,73,89,108,120,126],"Cebuano":[13],"Across":[14],"Scoring":[15],"Conventions":[16],"Language":[18],"Coverage\"":[19],"(paper":[20],"NJ":[21],"105).":[22],"It":[23],"contains":[24],"unnormalized":[26],"per-utterance":[27],"hypotheses":[28],"of":[29,33,82,99],"all":[30,77],"fourteen":[31],"runs":[32],"Whisper":[34],"large-v3,":[35],"MMS-1B-all,":[36],"SeamlessM4T":[38,85],"v2":[39],"Large":[40],"on":[41,140],"FLEURS":[43,118],"fil_ph":[44],"ceb_ph":[46],"test":[47],"splits;":[48],"run":[50],"configurations,":[51],"environment":[52],"specification,":[53],"exact":[55],"model":[56],"revisions;":[57],"inference":[59],"scoring":[61],"notebook":[62],"with":[63,88],"four":[65],"normalization":[66],"conventions,":[67],"scoring,":[68],"alignment,":[69],"bootstrap":[71],"code":[72],"its":[74],"worked-example":[75],"tests;":[76],"result":[78],"tables;":[79],"a":[80],"re-execution":[81],"published":[84],"decoding":[86],"path":[87],"without":[90],"special-token":[91],"suppression;":[92],"language-identity":[94],"audit":[95],"outputs;":[96],"labels":[98],"two":[100],"independent":[101],"annotators":[102],"46-utterance":[105],"validation":[106],"sample;":[107],"Cebuano\u2013Tagalog":[110],"word":[111],"list":[112],"used":[113],"in":[114],"substitution":[116],"analysis.":[117],"audio":[119],"reference":[121],"transcriptions":[122],"are":[123],"not":[124],"redistributed":[125],"should":[127],"be":[128],"obtained":[129],"from":[130],"google/fleurs":[131],"(CC":[132],"BY":[133],"4.0);":[134],"every":[135],"file":[136],"joins":[137],"to":[138],"it":[139],"idx":[141],"or":[142],"utt_id.":[143],"See":[144],"README.md":[145],"inside":[146],"details.":[150]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-29T00:00:00"}
