{"id":"https://openalex.org/W4412945601","doi":"https://doi.org/10.18653/v1/2025.acl-long.370","title":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning","display_name":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945601","doi":"https://doi.org/10.18653/v1/2025.acl-long.370"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.370","pdf_url":"https://aclanthology.org/2025.acl-long.370.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.370.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mingfei Lau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingfei Lau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072345219","display_name":"Yeming Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yeming Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385892","display_name":"Tingting Xu","orcid":"https://orcid.org/0000-0001-5524-035X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingting Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076026485","display_name":"Tongzhou Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tongzhou Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015194760","display_name":"Pavel Golik","orcid":"https://orcid.org/0000-0002-0977-4219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Golik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7466","last_page":"7492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.942799985408783,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.942799985408783,"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/computer-science","display_name":"Computer science","score":0.755618691444397},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5932429432868958},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5186928510665894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38228151202201843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3814479112625122},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3271997570991516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755618691444397},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5932429432868958},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5186928510665894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38228151202201843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3814479112625122},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3271997570991516},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.370","pdf_url":"https://aclanthology.org/2025.acl-long.370.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.370","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.370","pdf_url":"https://aclanthology.org/2025.acl-long.370.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945601.pdf","grobid_xml":"https://content.openalex.org/works/W4412945601.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W4387849428","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Our":[0],"quality":[1,26,49,95],"audit":[2],"for":[3,83],"three":[4],"widely":[5],"used":[6],"public":[7],"multilingual":[8],"speech":[9,132],"datasets-Mozilla":[10],"Common":[11],"Voice":[12],"17.0,":[13],"FLEURS,":[14],"and":[15,40,43,55,92,111,130],"VoxPopuli-shows":[16],"that":[17,58,79],"in":[18,64,97,117,127],"some":[19],"languages,":[20],"these":[21,30,34,48,115],"datasets":[22,35],"suffer":[23],"from":[24],"significant":[25],"issues.We":[27],"believe":[28],"addressing":[29],"issues":[31,50,60,116],"will":[32],"make":[33],"more":[36,62],"useful":[37],"as":[38],"training":[39],"evaluation":[41],"sets,":[42],"improve":[44],"downstream":[45],"models.We":[46],"divide":[47],"into":[51],"two":[52],"categories:":[53],"micro-level":[54],"macro-level.We":[56],"find":[57],"macro-level":[59],"are":[61],"prevalent":[63],"less":[65],"institutionalized,":[66],"often":[67],"under-resourced":[68],"languages.We":[69],"provide":[70],"a":[71],"case":[72],"analysis":[73],"of":[74,100,124],"Taiwanese":[75],"Southern":[76],"Min":[77],"(nan_tw)":[78],"highlights":[80],"the":[81,98,122],"need":[82],"proactive":[84],"language":[85],"planning":[86],"(e.g.orthography":[87],"prescriptions,":[88],"dialect":[89],"boundary":[90],"definition)":[91],"enhanced":[93],"data":[94,133],"control":[96],"process":[99],"Automatic":[101],"Speech":[102],"Recognition":[103],"(ASR)":[104],"dataset":[105,119],"creation.We":[106],"conclude":[107],"by":[108],"proposing":[109],"guidelines":[110],"recommendations":[112],"to":[113],"mitigate":[114],"future":[118],"development,":[120],"emphasizing":[121],"importance":[123],"sociolinguistic":[125],"awareness":[126],"creating":[128],"robust":[129],"reliable":[131],"resources.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}