{"id":"https://openalex.org/W10477584","doi":"https://doi.org/10.21437/interspeech.2011-789","title":"Efficient harvesting of internet audio for resource-scarce ASR","display_name":"Efficient harvesting of internet audio for resource-scarce ASR","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W10477584","doi":"https://doi.org/10.21437/interspeech.2011-789","mag":"10477584"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://researchspace.csir.co.za/dspace/bitstream/handle/10204/5769/Davel_2011.pdf?sequence=1&isAllowed=y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019780560","display_name":"Marelie H. Davel","orcid":"https://orcid.org/0000-0003-3103-5858"},"institutions":[{"id":"https://openalex.org/I66760702","display_name":"Council of Scientific and Industrial Research","ror":"https://ror.org/021wm7p51","country_code":"IN","type":"government","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Marelie H. Davel","raw_affiliation_strings":["Council of Scientific and Industrial Research, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Council of Scientific and Industrial Research, New Delhi, India","institution_ids":["https://openalex.org/I66760702"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050954463","display_name":"Charl van Heerden","orcid":"https://orcid.org/0000-0002-3212-2147"},"institutions":[{"id":"https://openalex.org/I66760702","display_name":"Council of Scientific and Industrial Research","ror":"https://ror.org/021wm7p51","country_code":"IN","type":"government","lineage":["https://openalex.org/I2799351866","https://openalex.org/I4210134808","https://openalex.org/I66760702"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Charl van Heerden","raw_affiliation_strings":["Council of Scientific and Industrial Research, New Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Council of Scientific and Industrial Research, New Delhi, India","institution_ids":["https://openalex.org/I66760702"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087231269","display_name":"Neil Kleynhans","orcid":null},"institutions":[{"id":"https://openalex.org/I21360634","display_name":"Council for Scientific and Industrial Research","ror":"https://ror.org/05j00sr48","country_code":"ZA","type":"government","lineage":["https://openalex.org/I21360634"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Neil Kleynhans","raw_affiliation_strings":["Council for Scientific and Industrial Research, Pretoria, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Council for Scientific and Industrial Research, Pretoria, South Africa","institution_ids":["https://openalex.org/I21360634"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032161971","display_name":"Etienne Barnard","orcid":"https://orcid.org/0000-0003-2202-2369"},"institutions":[{"id":"https://openalex.org/I27765905","display_name":"North-West University","ror":"https://ror.org/010f1sq29","country_code":"ZA","type":"education","lineage":["https://openalex.org/I27765905"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Etienne Barnard","raw_affiliation_strings":["North-West University, Potchefstroom, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North-West University, Potchefstroom, South Africa","institution_ids":["https://openalex.org/I27765905"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3153","last_page":"3156"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13194","display_name":"ICT in Developing Communities","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13194","display_name":"ICT in Developing Communities","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9656999707221985,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9503999948501587,"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":0.8445397615432739},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.686500608921051},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5668038129806519},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5074071288108826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4954794645309448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.452188640832901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41012927889823914},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19862601161003113},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1072944700717926},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08000099658966064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445397615432739},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.686500608921051},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5668038129806519},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5074071288108826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4954794645309448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.452188640832901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41012927889823914},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19862601161003113},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1072944700717926},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08000099658966064},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.nwu.ac.za:10394/26541","is_oa":true,"landing_page_url":"http://hdl.handle.net/10394/26541","pdf_url":"https://researchspace.csir.co.za/dspace/bitstream/handle/10204/5769/Davel_2011.pdf?sequence=1&isAllowed=y","source":{"id":"https://openalex.org/S4306402268","display_name":"Boloka Institutional Repository (North-west University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Presentation"}],"best_oa_location":{"id":"pmh:oai:dspace.nwu.ac.za:10394/26541","is_oa":true,"landing_page_url":"http://hdl.handle.net/10394/26541","pdf_url":"https://researchspace.csir.co.za/dspace/bitstream/handle/10204/5769/Davel_2011.pdf?sequence=1&isAllowed=y","source":{"id":"https://openalex.org/S4306402268","display_name":"Boloka Institutional Repository (North-west University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114027177","host_organization_name":"University of North Carolina at Chapel Hill","host_organization_lineage":["https://openalex.org/I114027177"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Presentation"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334105","display_name":"Center for High Performance Computing","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W10477584.pdf","grobid_xml":"https://content.openalex.org/works/W10477584.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W64751979","https://openalex.org/W85707815","https://openalex.org/W104056551","https://openalex.org/W1517939602","https://openalex.org/W1975113979","https://openalex.org/W2101885596","https://openalex.org/W2108776455","https://openalex.org/W2112032806","https://openalex.org/W2119728341"],"related_works":["https://openalex.org/W2370205415","https://openalex.org/W2065457896","https://openalex.org/W3173234801","https://openalex.org/W4387493491","https://openalex.org/W2904225411","https://openalex.org/W2167984027","https://openalex.org/W4388331409","https://openalex.org/W3021302227","https://openalex.org/W10630519","https://openalex.org/W2061937230"],"abstract_inverted_index":{"Spoken":[0],"recordings":[1,28],"that":[2],"have":[3,31],"been":[4,45],"transcribed":[5],"for":[6,11],"human":[7],"reading
\\n(e.g.":[8],"as":[9],"captions":[10],"audiovisual":[12],"material,":[13],"or":[14,53],"to":[15,20,33,47,57,127],"provide":[16],"alternative
\\nmodes":[17],"of":[18,37,64,112],"access":[19],"recordings)":[21],"are":[22],"widely":[23],"available":[24,73],"in":[25,40,51,133],"many
\\nlanguages.":[26],"Such":[27],"and":[29,97,117],"transcriptions":[30,99],"proven":[32],"be
\\na":[34],"valuable":[35],"source":[36],"ASR":[38,68,92],"data":[39,60],"well-resourced":[41],"languages,":[42],"but
\\nhave":[43],"not":[44,72],"exploited":[46],"a":[48,65,83,105,113,129],"significant":[49],"extent":[50],"under-resourced
\\nlanguages":[52],"dialects.":[54],"Techniques":[55],"used":[56,126],"harvest":[58],"such":[59],"typically
\\nassume":[61],"the":[62,101,110],"availability":[63],"fairly":[66],"accurate":[67],"system,
\\nwhich":[69],"is":[70,88],"generally":[71],"when":[74],"working":[75],"with":[76,95,122,136],"resourcescarce
\\nlanguages.":[77],"In":[78],"this":[79,119],"work,":[80],"we":[81],"define":[82],"process":[84],"whereby":[85],"an
\\nASR":[86],"corpus":[87,132],"bootstrapped":[89],"using":[90],"unmatched":[91],"models":[93],"in
\\nconjunction":[94],"speech":[96],"approximate":[98],"sourced
\\nfrom":[100],"Internet.":[102],"We":[103],"introduce":[104],"new":[106],"segmentation":[107],"technique
\\nbased":[108],"on":[109],"use":[111],"phone-internal":[114],"garbage":[115],"model,":[116],"demonstrate
\\nhow":[118],"technique":[120],"(combined":[121],"limited":[123],"filtering)":[124],"can
\\nbe":[125],"develop":[128],"large,":[130],"high-quality":[131],"an":[134],"underresourced
\\ndialect":[135],"minimal":[137],"effort.":[138]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}