{"id":"https://openalex.org/W4385807461","doi":"https://doi.org/10.21437/interspeech.2023-1979","title":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","display_name":"Zambezi Voice: A Multilingual Speech Corpus for Zambian Languages","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385807461","doi":"https://doi.org/10.21437/interspeech.2023-1979"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1979","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5039333739","display_name":"Claytone Sikasote","orcid":"https://orcid.org/0009-0004-1372-4662"},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":true,"raw_author_name":"Claytone Sikasote","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092120669","display_name":"Kalinda Siaminwe","orcid":null},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"Kalinda Siaminwe","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092120670","display_name":"Stanly Mwape","orcid":null},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"Stanly Mwape","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092120671","display_name":"Bangiwe Zulu","orcid":null},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"Bangiwe Zulu","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104155879","display_name":"Mofya Phiri","orcid":null},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"Mofya Phiri","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104155880","display_name":"Martin Phiri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Phiri","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015135687","display_name":"David Zulu","orcid":null},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"David Zulu","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045408669","display_name":"Mayumbo Nyirenda","orcid":"https://orcid.org/0000-0002-9615-3487"},"institutions":[{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["ZM"],"is_corresponding":false,"raw_author_name":"Mayumbo Nyirenda","raw_affiliation_strings":["University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013793053","display_name":"Antonios Anastasopoulos","orcid":"https://orcid.org/0000-0002-8544-246X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]},{"id":"https://openalex.org/I33278361","display_name":"University of Zambia","ror":"https://ror.org/03gh19d69","country_code":"ZM","type":"education","lineage":["https://openalex.org/I33278361"]}],"countries":["US","ZM"],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":["George Mason University, U.S.A","University of Zambia, Zambia"],"affiliations":[{"raw_affiliation_string":"George Mason University, U.S.A","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"University of Zambia, Zambia","institution_ids":["https://openalex.org/I33278361"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5039333739"],"corresponding_institution_ids":["https://openalex.org/I33278361"],"apc_list":null,"apc_paid":null,"fwci":0.8641,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78863104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3984","last_page":"3988"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.8234959244728088},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.642951488494873},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5902575850486755},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5399773716926575},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5364831686019897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5112380981445312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49341097474098206},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.44247227907180786},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4326520562171936},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2748905420303345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8234959244728088},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.642951488494873},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5902575850486755},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5399773716926575},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5364831686019897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5112380981445312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49341097474098206},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.44247227907180786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4326520562171936},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2748905420303345},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1979","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4331521547","display_name":"Collaborative Research: Language Documentation with an Artificial Intelligence (AI) Helper","funder_award_id":"2109578","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1663984431","https://openalex.org/W2134800885","https://openalex.org/W2585654394","https://openalex.org/W2933138175","https://openalex.org/W2963250244","https://openalex.org/W2979826702","https://openalex.org/W2995181338","https://openalex.org/W3015783745","https://openalex.org/W3030437843","https://openalex.org/W3035032094","https://openalex.org/W3036601975","https://openalex.org/W3092424727","https://openalex.org/W3157070662","https://openalex.org/W3174056976","https://openalex.org/W3198429080","https://openalex.org/W3213029956","https://openalex.org/W4224308495","https://openalex.org/W4283320359","https://openalex.org/W4287330433","https://openalex.org/W4385245566","https://openalex.org/W4385572115","https://openalex.org/W4388562892"],"related_works":["https://openalex.org/W2147998355","https://openalex.org/W1987021544","https://openalex.org/W4388404911","https://openalex.org/W2066051122","https://openalex.org/W2022789108","https://openalex.org/W2105439218","https://openalex.org/W2009814707","https://openalex.org/W2084281858","https://openalex.org/W2111751477","https://openalex.org/W2251328660"],"abstract_inverted_index":{"This":[0],"work":[1],"introduces":[2],"ZambeziVoice,":[3],"an":[4],"open-source":[5],"multilingual":[6,59,76,93],"speech":[7,38,52,60,77,100],"resource":[8],"for":[9,51,63,80,103],"Zambian":[10,81],"languages.It":[11],"contains":[12],"two":[13],"collections":[14],"of":[15,20,36],"datasets:":[16],"unlabelled":[17],"audio":[18],"recordings":[19],"radio":[21],"news":[22],"and":[23,29,66,85],"talk":[24],"shows":[25],"programs":[26],"(160":[27],"hours)":[28,34],"labelled":[30],"data":[31],"(over":[32],"80":[33],"consisting":[35],"read":[37],"recorded":[39],"from":[40,43],"text":[41],"sourced":[42],"publicly":[44,110],"available":[45],"literature":[46],"books.The":[47],"dataset":[48,78,107],"is":[49,73,108],"created":[50,79],"recognition":[53,101],"but":[54],"can":[55],"be":[56],"extended":[57],"to":[58,96],"processing":[61],"research":[62],"both":[64],"supervised":[65],"unsupervised":[67],"learning":[68,88],"approaches.To":[69],"our":[70,104],"knowledge,":[71],"this":[72],"the":[74,91],"first":[75],"languages.We":[82],"exploit":[83],"pretraining":[84],"cross-lingual":[86],"transfer":[87],"by":[89],"finetuning":[90],"Wav2Vec2.0large-scale":[92],"pretrained":[94],"model":[95],"build":[97],"end-to-end":[98],"(E2E)":[99],"models":[102],"baseline":[105],"models.The":[106],"released":[109],"under":[111],"a":[112],"Creative":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}