{"id":"https://openalex.org/W7140093973","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.14","title":"Tone in Yoruba ASR: Evaluating the Impact of Tone Recognition on Transformer-Based ASR Models","display_name":"Tone in Yoruba ASR: Evaluating the Impact of Tone Recognition on Transformer-Based ASR Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140093973","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.14"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.loreslm-1.14","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.14","pdf_url":"https://aclanthology.org/2026.loreslm-1.14.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.loreslm-1.14.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130407479","display_name":"Joy Olusanya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45711476","display_name":"Obafemi Awolowo University","ror":"https://ror.org/04snhqa82","country_code":"NG","type":"education","lineage":["https://openalex.org/I45711476"]}],"countries":["NG"],"is_corresponding":true,"raw_author_name":"Joy Olusanya","raw_affiliation_strings":["Department of Linguistics and African Languages Obafemi Awolowo University Ile-Ife , Nigeria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics and African Languages Obafemi Awolowo University Ile-Ife , Nigeria","institution_ids":["https://openalex.org/I45711476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5130407479"],"corresponding_institution_ids":["https://openalex.org/I45711476"],"apc_list":null,"apc_paid":null,"fwci":8.9362,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95210483,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/tone-recognition","display_name":"tone recognition","score":0.7929999828338623},{"id":"https://openalex.org/keywords/yoruba-language","display_name":"Yoruba","score":0.8579999804496765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7990000247955322},{"id":"https://openalex.org/keywords/speech-recognition-evaluation","display_name":"speech recognition evaluation","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.6935999989509583},{"id":"https://openalex.org/C2777568999","wikidata":"https://www.wikidata.org/wiki/Q34311","display_name":"Yoruba","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.41370001435279846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.28360000252723694},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2483000010251999}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.loreslm-1.14","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.14","pdf_url":"https://aclanthology.org/2026.loreslm-1.14.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.loreslm-1.14","doi":"https://doi.org/10.18653/v1/2026.loreslm-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.loreslm-1.14","pdf_url":"https://aclanthology.org/2026.loreslm-1.14.pdf","source":{"id":"https://openalex.org/S7407107604","display_name":"Workshop on Language Models for Low-Resource Languages (LoResLM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140093973.pdf","grobid_xml":"https://content.openalex.org/works/W7140093973.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W50444552","https://openalex.org/W178439087","https://openalex.org/W1525994142","https://openalex.org/W4385823369","https://openalex.org/W7213316368","https://openalex.org/W4402057031","https://openalex.org/W3171699967","https://openalex.org/W80870499","https://openalex.org/W7169682463","https://openalex.org/W7015568244"],"abstract_inverted_index":{"This":[0],"research":[1],"investigates":[2],"the":[3,124,153],"role":[4],"of":[5,116],"tone":[6,18,41,66,121,157],"in":[7,123],"Standard":[8],"Yoruba":[9,31,145],"Automatic":[10],"Speech":[11],"Recognition":[12],"(ASR),":[13],"focusing":[14],"on":[15,61],"how":[16],"explicit":[17],"marking":[19],"(diacritics)":[20],"influences":[21],"accuracy":[22],"and":[23,35,45,55,59,76,119,136,146,159,162],"overall":[24],"system":[25],"performance.As":[26],"a":[27],"lowresource":[28],"tonal":[29,117,149],"language,":[30],"encodes":[32],"critical":[33],"lexical":[34],"grammatical":[36],"contrasts":[37],"via":[38],"pitch,":[39],"making":[40],"handling":[42],"both":[43],"essential":[44],"challenging":[46],"for":[47,144,166],"ASR.Three":[48],"pre-trained":[49],"models,":[50],"Meta's":[51],"MMS-1B-all,":[52],"OpenAI's":[53],"Whisper-small,":[54],"AstralZander/Yoruba_ASR,":[56],"were":[57],"trained":[58],"evaluated":[60],"datasets":[62],"that":[63,100,129],"vary":[64],"by":[65],"annotation":[67],"(fully":[68],"tone-marked":[69,96],"vs.":[70],"non-tonemarked).Using":[71],"Word":[72],"Error":[73,78],"Rate":[74,79],"(WER)":[75],"Tone":[77],"(TER)":[80],"as":[81],"primary":[82],"metrics,":[83],"results":[84],"consistently":[85],"favoured":[86],"non-tone-marked":[87],"data,":[88],"yielding":[89],"substantially":[90],"lower":[91],"error":[92],"rates":[93],"than":[94],"their":[95],"counterparts.These":[97],"outcomes":[98],"suggest":[99],"current":[101],"architectures":[102],"encounter":[103],"difficulties":[104],"with":[105],"diacritically":[106],"marked":[107],"Yoruba,":[108],"likely":[109],"stemming":[110],"from":[111],"tokenisation":[112],"behaviour,":[113],"insufficient":[114],"representation":[115],"cues,":[118],"limited":[120],"modelling":[122],"underlying":[125],"pre-training.The":[126],"study":[127],"concludes":[128],"tone-aware":[130],"approaches,":[131],"spanning":[132],"tokenisation,":[133],"acoustic-text":[134],"alignment,":[135],"model":[137],"objectives,":[138],"are":[139],"necessary":[140],"to":[141],"improve":[142],"recognition":[143],"other":[147],"low-resource":[148],"languages.The":[150],"findings":[151],"clarify":[152],"interaction":[154],"between":[155],"linguistic":[156],"systems":[158],"computational":[160],"modelling,":[161],"offer":[163],"concrete":[164],"directions":[165],"building":[167],"more":[168],"robust,":[169],"tone-sensitive":[170],"ASR":[171],"systems.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}