{"id":"https://openalex.org/W4388008125","doi":"https://doi.org/10.1145/3617694.3623258","title":"Common Voice and accent choice: data contributors self-describe their spoken accents in diverse ways","display_name":"Common Voice and accent choice: data contributors self-describe their spoken accents in diverse ways","publication_year":2023,"publication_date":"2023-10-29","ids":{"openalex":"https://openalex.org/W4388008125","doi":"https://doi.org/10.1145/3617694.3623258"},"language":"en","primary_location":{"id":"doi:10.1145/3617694.3623258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617694.3623258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617694.3623258","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Equity and Access in Algorithms, Mechanisms, and Optimization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3617694.3623258","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077335303","display_name":"K. B. Reid","orcid":"https://orcid.org/0000-0001-9205-0942"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Kathy Reid","raw_affiliation_strings":["School of Cybernetics, Australian National University, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9205-0942","affiliations":[{"raw_affiliation_string":"School of Cybernetics, Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076408431","display_name":"E. Williams","orcid":"https://orcid.org/0000-0002-7895-458X"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Elizabeth T. Williams","raw_affiliation_strings":["School of Cybernetics, Australian National University, Australia"],"raw_orcid":"https://orcid.org/0000-0002-7895-458X","affiliations":[{"raw_affiliation_string":"School of Cybernetics, Australian National University, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077335303"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":3.5839,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93069493,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11640","display_name":"Linguistic Variation and Morphology","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3310","display_name":"Linguistics and Language"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12353","display_name":"Lexicography and Language Studies","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"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/stress","display_name":"Stress (linguistics)","score":0.874639093875885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7000594139099121},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.543660044670105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5407580733299255},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5292631387710571},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.510127604007721},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3871147930622101},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.15512818098068237}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.874639093875885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7000594139099121},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.543660044670105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5407580733299255},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5292631387710571},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.510127604007721},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3871147930622101},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.15512818098068237},{"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:10.1145/3617694.3623258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617694.3623258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617694.3623258","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Equity and Access in Algorithms, Mechanisms, and Optimization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3617694.3623258","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617694.3623258","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617694.3623258","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Equity and Access in Algorithms, Mechanisms, and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327705","display_name":"Mozilla Foundation","ror":"https://ror.org/01y8r3379"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388008125.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W340338119","https://openalex.org/W401183204","https://openalex.org/W636892609","https://openalex.org/W1485342627","https://openalex.org/W1526023455","https://openalex.org/W2007786502","https://openalex.org/W2072080435","https://openalex.org/W2125649282","https://openalex.org/W2165054306","https://openalex.org/W2168676811","https://openalex.org/W2749170691","https://openalex.org/W2806834802","https://openalex.org/W2910917352","https://openalex.org/W2950008337","https://openalex.org/W2978315362","https://openalex.org/W2990693156","https://openalex.org/W3005082021","https://openalex.org/W3012624518","https://openalex.org/W3014621527","https://openalex.org/W3030485994","https://openalex.org/W3033326607","https://openalex.org/W3040201034","https://openalex.org/W3112849432","https://openalex.org/W3122723859","https://openalex.org/W3170804539","https://openalex.org/W3208049241","https://openalex.org/W3215236363","https://openalex.org/W4205191555","https://openalex.org/W4213446427","https://openalex.org/W4226460991","https://openalex.org/W4240494537","https://openalex.org/W4244755608","https://openalex.org/W4285307558","https://openalex.org/W4323537001","https://openalex.org/W4387872955"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W162378616","https://openalex.org/W4251666207","https://openalex.org/W2087397317","https://openalex.org/W2350046259"],"abstract_inverted_index":{"The":[0,17],"use":[1,124],"of":[2,28,69,106,158],"machine":[3],"learning":[4],"(ML)-powered":[5],"speech":[6,22,198],"technologies":[7],"has":[8,123],"increased":[9],"significantly":[10],"in":[11,61,134,149,174,197],"recent":[12],"years":[13],"[40,":[14],"56,":[15],"72].":[16],"datasets":[18,79,175],"used":[19,42],"for":[20,50,168,177],"training":[21,46],"models":[23],"often":[24],"represent":[25],"demographic":[26],"features":[27],"the":[29,45,66,114,121],"speaker":[30],"\u2013":[31],"such":[32],"as":[33],"gender,":[34],"age,":[35],"and":[36,48,90,139,184,200],"accent.":[37],"These":[38],"axes":[39],"are":[40,84,131,137,172],"frequently":[41],"to":[43,65,80,193],"evaluate":[44],"set":[47,157],"model":[49],"bias":[51,196],"[52].":[52],"Here,":[53],"we":[54,185],"focus":[55],"on":[56,76],"how":[57,82,170],"accent":[58,70,107,195],"is":[59,146,160,182],"represented":[60,133,173],"voice":[62,78],"data":[63,199],"due":[64],"adverse":[67],"consequences":[68],"bias.":[71],"We":[72,87,109,127],"perform":[73],"document":[74],"analysis":[75],"several":[77],"identify":[81],"accents":[83,93,130,151,171],"currently":[85,132],"represented.":[86],"then":[88],"analyse":[89],"visualise":[91],"speaker-described":[92,150],"from":[94,152],"Mozilla\u2019s":[95],"Common":[96],"Voice":[97],"(CV)":[98],"v13":[99,116],"English":[100],"dataset,":[101,118],"forming":[102],"an":[103],"emergent":[104],"taxonomy":[105,122,192],"descriptors.":[108],"repeat":[110],"this":[111,144],"process":[112],"using":[113],"CV":[115],"Kiswahili":[117],"demonstrating":[119],"that":[120,129,136,189],"beyond":[125],"English.":[126],"find":[128],"ways":[135],"geographically,":[138],"predominantly,":[140],"nationally":[141],"bound.":[142],"While":[143],"pattern":[145],"also":[147],"shown":[148],"CV,":[153],"a":[154],"more":[155],"diverse":[156],"descriptors":[159],"revealed.":[161],"This":[162],"work":[163,188],"provides":[164],"some":[165],"early":[166],"evidence":[167],"re-thinking":[169],"intended":[176],"ML":[178],"applications.":[179],"Our":[180],"tooling":[181],"open-sourced,":[183],"invite":[186],"further":[187],"uses":[190],"our":[191],"assess":[194],"models.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}