{"id":"https://openalex.org/W4408352059","doi":"https://doi.org/10.1109/icassp49660.2025.10890761","title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","display_name":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352059","doi":"https://doi.org/10.1109/icassp49660.2025.10890761"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5096957275","display_name":"Turi Abu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Turi Abu","raw_affiliation_strings":["BNRist,Center for Speech and Language Technologies,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist,Center for Speech and Language Technologies,Beijing","institution_ids":["https://openalex.org/I4210107233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631944","display_name":"Shi Ying","orcid":"https://orcid.org/0000-0003-4291-5586"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ying Shi","raw_affiliation_strings":["BNRist,Center for Speech and Language Technologies,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist,Center for Speech and Language Technologies,Beijing","institution_ids":["https://openalex.org/I4210107233"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["BNRist,Center for Speech and Language Technologies,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist,Center for Speech and Language Technologies,Beijing","institution_ids":["https://openalex.org/I4210107233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I4210107233","display_name":"Language Science (South Korea)","ror":"https://ror.org/01h9v1373","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210107233"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["BNRist,Center for Speech and Language Technologies,Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist,Center for Speech and Language Technologies,Beijing","institution_ids":["https://openalex.org/I4210107233"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107233"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9879999756813049,"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/T13504","display_name":"African history and culture analysis","score":0.9745000004768372,"subfield":{"id":"https://openalex.org/subfields/3320","display_name":"Political Science and International Relations"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8138725757598877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6742214560508728},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6679085493087769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5494189262390137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45002609491348267},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14041253924369812},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.0730040967464447}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8138725757598877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6742214560508728},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6679085493087769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5494189262390137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45002609491348267},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14041253924369812},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0730040967464447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2137630452","https://openalex.org/W2936774411","https://openalex.org/W3015889230","https://openalex.org/W3097777922","https://openalex.org/W3100732527","https://openalex.org/W3196824004","https://openalex.org/W3197478142","https://openalex.org/W4296069332","https://openalex.org/W4387665148","https://openalex.org/W4392487628","https://openalex.org/W6624989032","https://openalex.org/W6638575559","https://openalex.org/W6664600640","https://openalex.org/W6692361679","https://openalex.org/W6692621364","https://openalex.org/W6693820377","https://openalex.org/W6739901393","https://openalex.org/W6745378982","https://openalex.org/W6770514103","https://openalex.org/W6778636411","https://openalex.org/W6791169292","https://openalex.org/W6810321870","https://openalex.org/W6847363464","https://openalex.org/W6851061970","https://openalex.org/W6859589467"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,13,27,31,92,120],"novel":[3],"Automatic":[4],"Speech":[5],"Recognition":[6],"(ASR)":[7],"dataset":[8,23,61,147],"for":[9,66,69,80,130,140,158],"the":[10,63,70,81,88,115,135,138],"Oromo":[11,71,131,164],"language,":[12],"widely":[14],"spoken":[15],"language":[16,72],"in":[17,54,119,144,163],"Ethiopia":[18],"and":[19,36,57,102,105,137,153,161],"neighboring":[20],"regions.":[21],"The":[22,146],"was":[24],"collected":[25],"through":[26],"crowdsourcing":[28],"initiative,":[29],"encompassing":[30],"diverse":[32],"range":[33],"of":[34,41,44,97,107,124],"speakers":[35],"phonetic":[37],"variations.":[38],"It":[39],"consists":[40],"100":[42],"hours":[43],"real-world":[45],"audio":[46],"recordings":[47],"paired":[48],"with":[49,99,109],"transcriptions,":[50],"covering":[51],"read":[52],"speech":[53,165],"both":[55,134],"clean":[56],"noisy":[58],"environments.":[59],"This":[60],"addresses":[62],"critical":[64],"need":[65],"ASR":[67,82,142],"resources":[68],"which":[73],"is":[74,148],"underrepresented.":[75],"To":[76],"show":[77],"its":[78,156],"applicability":[79],"task,":[83],"we":[84,154],"conducted":[85],"experiments":[86],"using":[87],"Conformer":[89],"model,":[90],"achieving":[91],"Word":[93],"Error":[94],"Rate":[95],"(WER)":[96],"15.32%":[98],"hybrid":[100],"CTC":[101,111],"AED":[103],"loss":[104],"WER":[106,123],"18.74%":[108],"pure":[110],"loss.":[112],"Additionally,":[113],"fine-tuning":[114],"Whisper":[116],"model":[117],"resulted":[118],"significantly":[121],"improved":[122],"10.82%.":[125],"These":[126],"results":[127],"establish":[128],"baselines":[129],"ASR,":[132],"highlighting":[133],"challenges":[136],"potential":[139],"improving":[141],"performance":[143],"Oromo.":[145],"publicly":[149],"available":[150],"at":[151],"https://github.com/turinaf/sagalee":[152],"encourage":[155],"use":[157],"further":[159],"research":[160],"development":[162],"processing.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}