{"id":"https://openalex.org/W4416798656","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249066","title":"Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal","display_name":"Characterization of Speech Similarity Between Australian Aboriginal and High-Resource Languages: A Case Study on Dharawal","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798656","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249066"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071116593","display_name":"Ting Dang","orcid":"https://orcid.org/0000-0003-3806-1493"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ting Dang","raw_affiliation_strings":["The University of Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne,Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044407068","display_name":"Trini Manoj Jeyaseelan","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Trini Manoj Jeyaseelan","raw_affiliation_strings":["The University of New South Wales,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028116210","display_name":"Eliathamby Ambikairajah","orcid":"https://orcid.org/0000-0003-4673-6534"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Eliathamby Ambikairajah","raw_affiliation_strings":["The University of New South Wales,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales,Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032689109","display_name":"Vidhyasaharan Sethu","orcid":"https://orcid.org/0000-0001-8492-1787"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vidhyasaharan Sethu","raw_affiliation_strings":["The University of New South Wales,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of New South Wales,Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39363249,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"658","last_page":"663"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.21040000021457672,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/T12090","display_name":"Language and cultural evolution","score":0.21040000021457672,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.149399995803833,"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/T13194","display_name":"ICT in Developing Communities","score":0.050599999725818634,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/similarity","display_name":"Similarity (geometry)","score":0.6776999831199646},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6101999878883362},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5293999910354614},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4163999855518341},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.3953000009059906},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.33809998631477356},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.3278000056743622},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.32089999318122864}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6776999831199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6654000282287598},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6101999878883362},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5515000224113464},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4620000123977661},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.3953000009059906},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35659998655319214},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1026965472","https://openalex.org/W1973424671","https://openalex.org/W2886137759","https://openalex.org/W2906459023","https://openalex.org/W2964309797","https://openalex.org/W3139878283","https://openalex.org/W3165404421","https://openalex.org/W4200475319","https://openalex.org/W4205120146","https://openalex.org/W4387251641","https://openalex.org/W4390756754","https://openalex.org/W4392487628","https://openalex.org/W4392903956","https://openalex.org/W4392904673","https://openalex.org/W4408355885","https://openalex.org/W4415433477"],"related_works":[],"abstract_inverted_index":{"Australian":[0,61],"Aboriginal":[1,62],"languages":[2,85,130],"are":[3],"of":[4,156],"significant":[5],"cultural":[6],"and":[7,24,52,67,82,103,111,137,148,152,159],"linguistic":[8],"value":[9],"but":[10],"remain":[11],"severely":[12],"underrepresented":[13],"in":[14,29,116,162],"modern":[15],"speech":[16,21,26,45,55,78,90,127,164],"AI":[17],"systems.":[18],"While":[19],"state-of-the-art":[20],"foundation":[22],"models":[23],"automatic":[25],"recognition":[27],"excel":[28],"high-resource":[30,84],"settings,":[31],"they":[32],"often":[33],"struggle":[34],"to":[35,37,99],"generalize":[36],"lowresource":[38],"languages,":[39],"especially":[40],"those":[41],"lacking":[42],"clean,":[43],"annotated":[44],"data.":[46],"In":[47],"this":[48,73],"work,":[49],"we":[50,75],"collect":[51],"clean":[53],"a":[54,59,87],"dataset":[56],"for":[57,144,166],"Dharawal,":[58],"low-resource":[60],"language,":[63],"by":[64],"carefully":[65],"sourcing":[66],"processing":[68],"publicly":[69],"available":[70],"recordings.":[71],"Using":[72],"dataset,":[74],"analyze":[76],"the":[77,117,154],"similarity":[79,106,110,128],"between":[80],"Dharawal":[81,124],"107":[83],"using":[86,108],"pre-trained":[88],"multilingual":[89],"encoder.":[91],"Our":[92],"approach":[93],"combines":[94],"(1)":[95],"misclassification":[96],"rate":[97],"analysis":[98,161],"assess":[100],"language":[101,168],"confusability,":[102],"(2)":[104],"fine-grained":[105],"measurements":[107],"cosine":[109],"Fr\u00e9chet":[112],"Inception":[113],"Distance":[114],"(FID)":[115],"embedding":[118],"space.":[119],"Experimental":[120],"results":[121],"reveal":[122],"that":[123],"shares":[125],"strong":[126],"with":[129],"such":[131],"as":[132],"Latin,":[133],"M\u0101ori,":[134],"Korean,":[135],"Thai,":[136],"Welsh.":[138],"These":[139],"findings":[140],"offer":[141],"practical":[142],"guidance":[143],"future":[145],"transfer":[146],"learning":[147],"model":[149],"adaptation":[150],"efforts,":[151],"underscore":[153],"importance":[155],"data":[157],"collection":[158],"embedding-based":[160],"supporting":[163],"technologies":[165],"endangered":[167],"communities.":[169]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}