{"id":"https://openalex.org/W7225173171","doi":"https://doi.org/10.48550/arxiv.2611.02903","title":"Maswao: An automatically collected, prepared, and benchmarked dataset for the South African Sign language","display_name":"Maswao: An automatically collected, prepared, and benchmarked dataset for the South African Sign language","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225173171","doi":"https://doi.org/10.48550/arxiv.2611.02903"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02903","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02903","pdf_url":"https://arxiv.org/pdf/2611.02903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02903","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009492197","display_name":"Thapelo Sindane","orcid":"https://orcid.org/0000-0002-9754-9547","observed_orcids":["https://orcid.org/0000-0002-9754-9547"]},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Sindane, Thapelo","raw_affiliation_strings":["Data Science For Social Impact Lab Department of Computer Science University of Pretoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science For Social Impact Lab Department of Computer Science University of Pretoria","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119845513","display_name":"Unarine Netshifhefhe","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Netshifhefhe, Unarine","raw_affiliation_strings":["Data Science For Social Impact Lab Department of Computer Science University of Pretoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science For Social Impact Lab Department of Computer Science University of Pretoria","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060690192","display_name":"Vukosi N. Marivate","orcid":"https://orcid.org/0000-0002-6731-6267","observed_orcids":["https://orcid.org/0000-0002-6731-6267"]},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Marivate, Vukosi","raw_affiliation_strings":["Data Science For Social Impact Lab Department of Computer Science University of Pretoria Lelapa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science For Social Impact Lab Department of Computer Science University of Pretoria Lelapa AI","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042301177","display_name":"Abiodun Modupe","orcid":"https://orcid.org/0000-0002-9732-6466","observed_orcids":["https://orcid.org/0000-0002-9732-6466"]},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Modupe, Abiodun","raw_affiliation_strings":["Data Science For Social Impact Lab Department of Computer Science University of Pretoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science For Social Impact Lab Department of Computer Science University of Pretoria","institution_ids":["https://openalex.org/I69552723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160430406","display_name":"Herkulaas Combrink","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I26999989","display_name":"University of the Free State","ror":"https://ror.org/009xwd568","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26999989"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Combrink, Herkulaas","raw_affiliation_strings":["interdisciplinary center for digital futures Faculty of Economic and Management Sciences University of the Free State"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"interdisciplinary center for digital futures Faculty of Economic and Management Sciences University of the Free State","institution_ids":["https://openalex.org/I26999989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160558825","display_name":"Ketro Sithole","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I69552723","display_name":"University of Pretoria","ror":"https://ror.org/00g0p6g84","country_code":"ZA","type":"education","lineage":["https://openalex.org/I69552723"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Sithole, Ketro","raw_affiliation_strings":["Data Science For Social Impact Lab Department of Computer Science University of Pretoria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Science For Social Impact Lab Department of Computer Science University of Pretoria","institution_ids":["https://openalex.org/I69552723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.014000000432133675,"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/T11285","display_name":"Hearing Impairment and Communication","score":0.0031999999191612005,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/south-african-sign-language","display_name":"South African Sign Language","score":0.9909999966621399},{"id":"https://openalex.org/keywords/sign-language-dataset","display_name":"sign language dataset","score":0.7979999780654907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.6309999823570251},{"id":"https://openalex.org/keywords/sign-to-text-translation","display_name":"sign-to-text translation","score":0.847000002861023},{"id":"https://openalex.org/keywords/sign-language-translation","display_name":"sign language translation","score":0.5899999737739563},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.8029999732971191},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.7480000257492065},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864000201225281},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.692300021648407},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6761000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5379999876022339},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39660000801086426},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.3806999921798706},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.37369999289512634},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C2776737515","wikidata":"https://www.wikidata.org/wiki/Q14759","display_name":"American Sign Language","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C75778745","wikidata":"https://www.wikidata.org/wiki/Q342626","display_name":"Lag","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02903","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02903","pdf_url":"https://arxiv.org/pdf/2611.02903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.02903","doi":"https://doi.org/10.48550/arxiv.2611.02903","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02903","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02903","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02903","pdf_url":"https://arxiv.org/pdf/2611.02903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225173171.pdf","grobid_xml":"https://content.openalex.org/works/W7225173171.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7125611605","https://openalex.org/W7125121097","https://openalex.org/W7202139860","https://openalex.org/W4416131819","https://openalex.org/W7155359813","https://openalex.org/W7131851344","https://openalex.org/W4396814528","https://openalex.org/W4417053066","https://openalex.org/W4386302932","https://openalex.org/W4402854580"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,11,19,142,205],"sign":[3,39,53,87,139],"language":[4,88,140],"processing":[5,27],"can":[6],"be":[7],"attributed":[8],"to":[9,71,149,154,161,193,217],"developments":[10],"both":[12],"large-scale":[13],"dataset":[14,179],"collection":[15,83],"and":[16,31,46,84,145,190,224,233,245],"algorithmic":[17],"complexity":[18],"areas":[20],"such":[21,41,59,115],"as":[22,42,102,116,227,229],"pose":[23],"estimation":[24],"techniques,":[25],"signal":[26],"through":[28],"Transformer":[29,191,202,214],"models,":[30],"model":[32],"optimization.":[33],"However,":[34],"only":[35],"a":[36,78,103],"handful":[37],"of":[38,58,86,152,183,220],"languages,":[40,54],"the":[43,56,62,81,96,138,143,169,176,181,206,212,241],"American,":[44],"British,":[45],"German,":[47],"from":[48],"over":[49],"200":[50],"globally":[51],"recognized":[52],"reap":[55],"benefits":[57],"advancements,":[60],"while":[61],"rest":[63],"lag":[64],"behind.":[65],"In":[66],"this":[67,73],"study,":[68],"we":[69,106,120,136,174],"aim":[70],"address":[72],"technological":[74],"disparity":[75],"by":[76],"proposing":[77],"framework":[79],"for":[80],"automatic":[82],"preparation":[85],"datasets,":[89],"with":[90,211],"very":[91],"minimal":[92],"human-labour":[93],"intervention,":[94],"using":[95,112,128,186],"South":[97],"African":[98],"Sign":[99],"Language":[100],"(SASL)":[101],"testbed.":[104],"Specifically,":[105],"automatically":[107],"collect":[108],"SASL":[109],"video":[110],"content":[111],"public":[113],"resources":[114],"news":[117],"broadcasts.":[118],"Additionally,":[119],"convert":[121],"their":[122,195],"accompanying":[123],"audio":[124],"streams":[125],"into":[126],"text":[127],"available":[129],"Automatic":[130],"Speech":[131],"Recognition":[132],"(ASR)":[133],"tools.":[134],"Furthermore,":[135],"crop":[137],"area":[141],"videos":[144,160],"use":[146],"gradient":[147],"descent":[148],"locate":[150],"valleys":[151],"non-motion":[153],"determine":[155],"end-of-sentence":[156],"points":[157],"within":[158],"long":[159],"create":[162],"our":[163],"weakly":[164,177],"sentence-aligned":[165],"parallel":[166],"corpora":[167],"--":[168],"Maswao":[170],"(Signs)":[171],"dataset.":[172],"Finally,":[173],"benchmark":[175],"aligned":[178],"on":[180],"task":[182,242],"Sign-to-text":[184],"Translation":[185],"Recurrent":[187],"Neural":[188],"Networks":[189],"models":[192,203],"compare":[194],"individual":[196],"intricacies.":[197],"Our":[198],"results":[199,238],"show":[200],"that":[201,240],"proposed":[204],"literature":[207],"outperform":[208],"recurrent":[209],"baselines,":[210],"best-performing":[213],"achieving":[215],"BLEU-1":[216],"BLEU-4":[218],"scores":[219],"13.78,":[221],"5.21,":[222],"2.52,":[223],"1.54,":[225],"respectively,":[226],"well":[228],"ChrF":[230],"=":[231,235],"18.09":[232],"ROUGE-L":[234],"10.51.":[236],"These":[237],"indicate":[239],"remains":[243],"promising":[244],"warrants":[246],"further":[247],"investigations.":[248]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}