{"id":"https://openalex.org/W4377140520","doi":"https://doi.org/10.1145/3597494","title":"Swahili Speech Dataset Development and Improved Pre-training Method for Spoken Digit Recognition","display_name":"Swahili Speech Dataset Development and Improved Pre-training Method for Spoken Digit Recognition","publication_year":2023,"publication_date":"2023-05-20","ids":{"openalex":"https://openalex.org/W4377140520","doi":"https://doi.org/10.1145/3597494"},"language":"en","primary_location":{"id":"doi:10.1145/3597494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597494","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5091337893","display_name":"Alexander Rogath Kivaisi","orcid":"https://orcid.org/0000-0001-9184-3078"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Alexander R. Kivaisi","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0001-9184-3078","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044948606","display_name":"Qingjie Zhao","orcid":"https://orcid.org/0000-0002-6955-4170"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Zhao","raw_affiliation_strings":["Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology"],"raw_orcid":"https://orcid.org/0000-0002-6955-4170","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002506087","display_name":"Jimmy Mbelwa","orcid":"https://orcid.org/0000-0002-2263-3218"},"institutions":[{"id":"https://openalex.org/I182078086","display_name":"University of Dar es Salaam","ror":"https://ror.org/0479aed98","country_code":"TZ","type":"education","lineage":["https://openalex.org/I182078086"]}],"countries":["TZ"],"is_corresponding":false,"raw_author_name":"Jimmy T. Mbelwa","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Dar es salaam"],"raw_orcid":"https://orcid.org/0000-0002-2263-3218","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Dar es salaam","institution_ids":["https://openalex.org/I182078086"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1104,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.80679638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"22","issue":"7","first_page":"1","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/swahili","display_name":"Swahili","score":0.8799980878829956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032841682434082},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6066891551017761},{"id":"https://openalex.org/keywords/numerical-digit","display_name":"Numerical digit","score":0.5834676027297974},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5820899605751038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5635029673576355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508571982383728},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1454589068889618}],"concepts":[{"id":"https://openalex.org/C2779913364","wikidata":"https://www.wikidata.org/wiki/Q7838","display_name":"Swahili","level":2,"score":0.8799980878829956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032841682434082},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6066891551017761},{"id":"https://openalex.org/C94957134","wikidata":"https://www.wikidata.org/wiki/Q82990","display_name":"Numerical digit","level":2,"score":0.5834676027297974},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5820899605751038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5635029673576355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508571982383728},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1454589068889618},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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:10.1145/3597494","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597494","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320335564","display_name":"Chinese Government Scholarship","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1970663544","https://openalex.org/W1989966304","https://openalex.org/W2120209245","https://openalex.org/W2140304104","https://openalex.org/W2148154194","https://openalex.org/W2152591578","https://openalex.org/W2191779130","https://openalex.org/W2400486159","https://openalex.org/W2401271873","https://openalex.org/W2559932510","https://openalex.org/W2596989490","https://openalex.org/W2604292070","https://openalex.org/W2786459654","https://openalex.org/W2789300626","https://openalex.org/W2913851961","https://openalex.org/W2914120296","https://openalex.org/W2915722758","https://openalex.org/W2933976917","https://openalex.org/W2948080012","https://openalex.org/W2963303951","https://openalex.org/W2973049979","https://openalex.org/W2973132140","https://openalex.org/W3021720440","https://openalex.org/W3034124732","https://openalex.org/W3038734866","https://openalex.org/W3134079985","https://openalex.org/W3198059188","https://openalex.org/W4253129489","https://openalex.org/W4288376229","https://openalex.org/W6767737316","https://openalex.org/W6800638362"],"related_works":["https://openalex.org/W2023610355","https://openalex.org/W2589694904","https://openalex.org/W4232455167","https://openalex.org/W2197846837","https://openalex.org/W2966567079","https://openalex.org/W2064315740","https://openalex.org/W2528678572","https://openalex.org/W1964726137","https://openalex.org/W4312903783","https://openalex.org/W1515988320"],"abstract_inverted_index":{"Speech":[0],"dataset":[1,87],"is":[2,22],"an":[3,111,138],"essential":[4],"component":[5],"in":[6,168],"building":[7],"commercial":[8],"speech":[9,50],"applications.":[10],"However,":[11,52],"low-resource":[12],"languages":[13,29],"such":[14,18,31],"as":[15],"Swahili":[16,84,89,148],"lack":[17],"a":[19,83],"resource":[20],"that":[21,135,156],"vital":[23],"for":[24,69,88,116],"spoken":[25,70,85,90,105,117],"digit":[26,71,86,91,106,118],"recognition.":[27,51,72,92,107,119],"For":[28],"where":[30],"resources":[32,46],"exist,":[33],"they":[34],"are":[35],"usually":[36],"insufficient.":[37],"Thus,":[38],"pre-training":[39,66,102,114,133],"methods":[40,67,103],"have":[41],"been":[42],"used":[43],"with":[44,163],"external":[45],"to":[47,53,137],"improve":[48],"continuous":[49],"the":[54,63,96,124,132,165],"best":[55],"of":[56,65,98,126],"our":[57,157],"knowledge,":[58],"no":[59],"study":[60,74],"has":[61,123],"investigated":[62,95],"effect":[64,97],"specifically":[68],"This":[73],"aimed":[75],"at":[76],"addressing":[77],"these":[78],"problems.":[79],"First,":[80],"we":[81,94,109],"developed":[82],"Then,":[93],"cross-lingual":[99],"and":[100,152],"multi-lingual":[101],"on":[104,147],"Finally,":[108],"proposed":[110,121],"effective":[112],"language-independent":[113],"method":[115,122,158],"The":[120],"advantage":[125],"incorporating":[127],"target":[128],"language":[129],"data":[130],"during":[131],"stage":[134],"leads":[136],"optimal":[139],"solution":[140],"when":[141],"using":[142],"less":[143],"training":[144],"data.":[145],"Experiments":[146],"(being":[149],"developed),":[150],"English,":[151],"Gujarati":[153],"datasets":[154],"show":[155],"achieves":[159],"better":[160],"performance":[161],"compared":[162],"all":[164],"baselines":[166],"listed":[167],"this":[169],"study.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
