{"id":"https://openalex.org/W7163148000","doi":"https://doi.org/10.1109/access.2026.3699426","title":"Syllable Level Prosody and Self-Supervised Learning Fusion for Tone Recognition in Yor\u00f9b\u00e1 Speech","display_name":"Syllable Level Prosody and Self-Supervised Learning Fusion for Tone Recognition in Yor\u00f9b\u00e1 Speech","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163148000","doi":"https://doi.org/10.1109/access.2026.3699426"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3699426","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3699426","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3699426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005192380","display_name":"Charity Ojochogwu Egbunu","orcid":null},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Charity Ojochogwu Egbunu","raw_affiliation_strings":["Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia"],"raw_orcid":"https://orcid.org/0009-0003-4766-754X","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025201865","display_name":"Fadhilah Rosdi","orcid":"https://orcid.org/0000-0002-8614-1810"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Fadhilah Rosdi","raw_affiliation_strings":["Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-8614-1810","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123711539","display_name":"Mohammed Faidzul Nasrudin","orcid":null},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mohammed Faidzul Nasrudin","raw_affiliation_strings":["Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056541241","display_name":"Abdul Hadi Abd Rahman","orcid":"https://orcid.org/0000-0002-0261-073X"},"institutions":[{"id":"https://openalex.org/I885383172","display_name":"National University of Malaysia","ror":"https://ror.org/00bw8d226","country_code":"MY","type":"education","lineage":["https://openalex.org/I885383172"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Abdul Hadi Abd Rahman","raw_affiliation_strings":["Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia"],"raw_orcid":"https://orcid.org/0000-0002-0261-073X","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia","institution_ids":["https://openalex.org/I885383172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I885383172"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68710483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"84586","last_page":"84600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.44679999351501465,"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":0.44679999351501465,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.30320000648498535,"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/T10860","display_name":"Speech and Audio Processing","score":0.0674000009894371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7353000044822693},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6341000199317932},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4442000091075897},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36230000853538513},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.34940001368522644}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7353000044822693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7160999774932861},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604999899864197},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6341000199317932},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4214000105857849},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C3019728051","wikidata":"https://www.wikidata.org/wiki/Q7447757","display_name":"Tone burst","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26409998536109924}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3699426","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3699426","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:deb98d1a8c774044a1685f5075200188","is_oa":true,"landing_page_url":"https://doaj.org/article/deb98d1a8c774044a1685f5075200188","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":"IEEE Access, Vol 14, Pp 84586-84600 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3699426","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3699426","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4725664258003235}],"awards":[{"id":"https://openalex.org/G8432114582","display_name":null,"funder_award_id":"GGPM-2017-020","funder_id":"https://openalex.org/F4320322699","funder_display_name":"Universiti Kebangsaan Malaysia"}],"funders":[{"id":"https://openalex.org/F4320322699","display_name":"Universiti Kebangsaan Malaysia","ror":"https://ror.org/00bw8d226"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"tone":[1,87],"recognition":[2,88,213],"remains":[3],"difficult":[4],"for":[5,125,210],"Yor&#x00F9;b&#x00E1;,":[6],"a":[7,84,100,155,205],"low-resource":[8,217],"tonal":[9,55,119,196],"language,":[10],"largely":[11],"because":[12],"of":[13,158,163,190],"the":[14,20,25,109,114,141,188],"limited":[15],"annotated":[16],"speech":[17,212],"data":[18],"and":[19,27,74,149,160,173,182,198,207,214],"substantial":[21],"acoustic":[22,44,65],"overlap":[23],"between":[24],"Mid":[26],"Low":[28],"tones":[29],"in":[30,195,216],"continuous":[31],"speech.":[32],"Recent":[33],"self-supervised":[34],"learning":[35],"(SSL)":[36],"models,":[37],"such":[38],"as":[39,108],"wav2vec":[40],"2.0,":[41],"provide":[42],"rich":[43],"representations;":[45],"however,":[46],"these":[47,79],"embeddings":[48,98],"do":[49],"not":[50],"explicitly":[51],"encode":[52],"phonological":[53],"or":[54],"contexts.":[56],"In":[57],"contrast,":[58],"traditional":[59],"prosody-based":[60],"approaches":[61],"rely":[62],"on":[63,131],"handcrafted":[64],"cues":[66],"that":[67,90,121,140,200],"are":[68,122],"often":[69],"sensitive":[70],"to":[71,116,180],"speaker":[72],"variability":[73],"contextual":[75],"changes.":[76],"To":[77],"address":[78],"limitations,":[80],"this":[81],"study":[82],"proposes":[83],"syllable-level,":[85],"context-aware":[86],"framework":[89],"combines":[91],"explicit":[92],"prosodic":[93],"features":[94],"with":[95],"syllable-pooled":[96],"SSL":[97],"within":[99],"short-sequence":[101],"BiLSTM":[102],"model.":[103],"The":[104,152],"syllable":[105],"is":[106],"treated":[107],"fundamental":[110],"tone-bearing":[111],"unit,":[112],"allowing":[113],"model":[115,144],"capture":[117],"local":[118],"interactions":[120],"especially":[123],"important":[124],"resolving":[126],"Mid&#x2013;Low":[127],"ambiguities.":[128],"Experiments":[129],"conducted":[130],"114,974":[132],"labelled":[133],"syllables":[134],"using":[135],"five-fold":[136],"grouped":[137],"cross-validation":[138],"showed":[139],"proposed":[142],"fusion":[143,202],"consistently":[145],"outperformed":[146],"both":[147],"classical":[148],"neural":[150],"baselines.":[151],"system":[153],"achieves":[154],"Macro-F1":[156],"score":[157],"0.903":[159],"an":[161],"accuracy":[162],"0.901,":[164],"while":[165],"substantially":[166],"reducing":[167],"Mid<inline-formula>":[168],"<tex-math":[169,175],"notation=\"LaTeX\">$\\to":[170,176],"$":[171,177],"</tex-math></inline-formula>Low":[172],"Low<inline-formula>":[174],"</tex-math></inline-formula>Mid":[178],"confusions":[179],"2.73%":[181],"5.99%,":[183],"respectively.":[184],"These":[185],"findings":[186],"highlight":[187],"value":[189],"linguistically":[191],"grounded":[192],"design":[193],"choices":[194],"modelling":[197],"suggest":[199],"syllable-centric":[201],"strategies":[203],"offer":[204],"practical":[206],"transferable":[208],"solution":[209],"tone-aware":[211],"synthesis":[215],"languages.":[218]},"counts_by_year":[],"updated_date":"2026-06-09T06:18:44.609144","created_date":"2026-06-03T00:00:00"}
