{"id":"https://openalex.org/W2971222421","doi":"https://doi.org/10.3390/info10090268","title":"The Usefulness of Imperfect Speech Data for ASR Development in Low-Resource Languages","display_name":"The Usefulness of Imperfect Speech Data for ASR Development in Low-Resource Languages","publication_year":2019,"publication_date":"2019-08-28","ids":{"openalex":"https://openalex.org/W2971222421","doi":"https://doi.org/10.3390/info10090268","mag":"2971222421"},"language":"en","primary_location":{"id":"doi:10.3390/info10090268","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info10090268","pdf_url":"https://www.mdpi.com/2078-2489/10/9/268/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/10/9/268/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013657411","display_name":"Jaco Badenhorst","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jaco Badenhorst","raw_affiliation_strings":["Human Technologies Research Group, CSIR Next Generation Enterprises and Institutions Cluster, P.O. Box 395, Pretoria 0001, South Africa"],"affiliations":[{"raw_affiliation_string":"Human Technologies Research Group, CSIR Next Generation Enterprises and Institutions Cluster, P.O. Box 395, Pretoria 0001, South Africa","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020014097","display_name":"Febe de Wet","orcid":"https://orcid.org/0000-0003-3495-9802"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Febe de Wet","raw_affiliation_strings":["Department of Electrical &amp; Electronic Engineering, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South Africa","Human Technologies Research Group, CSIR Next Generation Enterprises and Institutions Cluster, P.O. Box 395, Pretoria 0001, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical &amp; Electronic Engineering, Stellenbosch University, Private Bag X1, Stellenbosch 7602, South Africa","institution_ids":["https://openalex.org/I26092322"]},{"raw_affiliation_string":"Human Technologies Research Group, CSIR Next Generation Enterprises and Institutions Cluster, P.O. Box 395, Pretoria 0001, South Africa","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013657411"],"corresponding_institution_ids":[],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.0109,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82897568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"9","first_page":"268","last_page":"268"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999111413955688},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7370714545249939},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.5866530537605286},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5139688849449158},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5030378699302673},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4638751745223999},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4309334456920624},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.42452871799468994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4211135506629944},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.22627082467079163},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15349572896957397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999111413955688},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7370714545249939},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.5866530537605286},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5139688849449158},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5030378699302673},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4638751745223999},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4309334456920624},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.42452871799468994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4211135506629944},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.22627082467079163},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15349572896957397},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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":3,"locations":[{"id":"doi:10.3390/info10090268","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info10090268","pdf_url":"https://www.mdpi.com/2078-2489/10/9/268/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3e174d6abec84e9fa932b2da07107a07","is_oa":true,"landing_page_url":"https://doaj.org/article/3e174d6abec84e9fa932b2da07107a07","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 10, Iss 9, p 268 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/10/9/268/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/info10090268","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info10090268","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info10090268","pdf_url":"https://www.mdpi.com/2078-2489/10/9/268/pdf","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2971222421.pdf","grobid_xml":"https://content.openalex.org/works/W2971222421.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W76778408","https://openalex.org/W104056551","https://openalex.org/W148837159","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1734538896","https://openalex.org/W1967940534","https://openalex.org/W1980013187","https://openalex.org/W2044138293","https://openalex.org/W2099170998","https://openalex.org/W2117671523","https://openalex.org/W2144411866","https://openalex.org/W2251689968","https://openalex.org/W2291868800","https://openalex.org/W2293634267","https://openalex.org/W2347041928","https://openalex.org/W2402146185","https://openalex.org/W2404568753","https://openalex.org/W2406536041","https://openalex.org/W2406566270","https://openalex.org/W2407080277","https://openalex.org/W2512147087","https://openalex.org/W2579416857","https://openalex.org/W2729190387","https://openalex.org/W2747135936","https://openalex.org/W2782717521","https://openalex.org/W2783699665","https://openalex.org/W2793131830","https://openalex.org/W2799316004","https://openalex.org/W2805341710","https://openalex.org/W2806050188","https://openalex.org/W2806666542","https://openalex.org/W2888867175","https://openalex.org/W2943615777","https://openalex.org/W2947322222","https://openalex.org/W2947729651","https://openalex.org/W6603616073","https://openalex.org/W6606109230","https://openalex.org/W6628468810","https://openalex.org/W6631362777","https://openalex.org/W6713658440","https://openalex.org/W6713670424","https://openalex.org/W6732770863","https://openalex.org/W6960287570"],"related_works":["https://openalex.org/W2374250903","https://openalex.org/W1546413948","https://openalex.org/W2263832889","https://openalex.org/W2243884323","https://openalex.org/W42072456","https://openalex.org/W4243095785","https://openalex.org/W4387894447","https://openalex.org/W2089057551","https://openalex.org/W2487056937","https://openalex.org/W2061937230"],"abstract_inverted_index":{"When":[0],"the":[1,22,34,65,71,105,113,125,133,141,148,187,190,193],"National":[2],"Centre":[3],"for":[4,17,44,64,70,84,172,183],"Human":[5],"Language":[6],"Technology":[7],"(NCHLT)":[8],"Speech":[9],"corpus":[10],"was":[11,81,102,109],"released,":[12],"it":[13,116],"created":[14],"various":[15],"opportunities":[16],"speech":[18,68],"technology":[19],"development":[20,54],"in":[21,37,48,96,112],"11":[23],"official,":[24],"but":[25,91,121],"critically":[26],"under-resourced,":[27],"languages":[28,46,74],"of":[29,57,59,67,124,150,186,192],"South":[30,72],"Africa.":[31],"Since":[32],"then,":[33],"substantial":[35],"improvements":[36],"acoustic":[38,154],"modeling":[39],"that":[40,86,108,136],"deep":[41],"architectures":[42],"achieved":[43],"well-resourced":[45],"ushered":[47],"a":[49,119,184],"new":[50],"data":[51,85,101,152,177],"requirement:":[52],"their":[53],"requires":[55],"hundreds":[56],"hours":[58],"speech.":[60],"A":[61],"suitable":[62],"strategy":[63],"enlargement":[66],"resources":[69,135],"African":[73],"is":[75],"therefore":[76],"required.":[77],"The":[78,156],"first":[79,131],"possibility":[80],"to":[82],"look":[83],"has":[87,92],"already":[88],"been":[89,94],"collected":[90,103],"not":[93,110],"included":[95,111],"an":[97],"existing":[98],"corpus.":[99],"Additional":[100],"during":[104],"NCHLT":[106,143,195],"project":[107],"official":[114],"corpus:":[115],"only":[117],"contains":[118],"curated,":[120],"limited":[122],"subset":[123],"data.":[126,144,196],"In":[127,175],"this":[128,151],"paper,":[129],"we":[130],"analyze":[132],"additional":[134],"could":[137],"be":[138],"harvested":[139],"from":[140],"auxiliary":[142,194],"We":[145],"also":[146],"measure":[147],"effect":[149],"on":[153],"modeling.":[155],"analysis":[157],"incorporates":[158],"recent":[159],"factorized":[160],"time-delay":[161],"neural":[162],"networks":[163],"(TDNN-F).":[164],"These":[165],"models":[166],"significantly":[167],"reduce":[168],"phone":[169],"error":[170],"rates":[171],"all":[173],"languages.":[174],"addition,":[176],"augmentation":[178],"and":[179],"cross-corpus":[180],"validation":[181],"experiments":[182],"number":[185],"datasets":[188],"illustrate":[189],"utility":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
