{"id":"https://openalex.org/W2032020816","doi":"https://doi.org/10.1109/asru.2007.4430173","title":"Data selection for speech recognition","display_name":"Data selection for speech recognition","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2032020816","doi":"https://doi.org/10.1109/asru.2007.4430173","mag":"2032020816"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/Data_Selection_for_Speech_Recognition/6604616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100668103","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0001-9057-5817"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Wu","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, USA","Carnegie Mellon University. Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University. Pittsburgh","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451786","display_name":"Rong Zhang","orcid":"https://orcid.org/0000-0002-2288-2847"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rong Zhang","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, USA","Carnegie Mellon University. Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University. Pittsburgh","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rudnicky","raw_affiliation_strings":["Language Technology Institute, Carnegie Mellon University, USA","Carnegie Mellon University. Pittsburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University. Pittsburgh","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"562","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9979000091552734,"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":0.8231158256530762},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7110201716423035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6659046411514282},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6061820387840271},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.551192045211792},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5471307039260864},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5352523922920227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49983668327331543},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35008758306503296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32785892486572266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231158256530762},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7110201716423035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6659046411514282},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6061820387840271},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.551192045211792},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5471307039260864},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5352523922920227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49983668327331543},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35008758306503296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32785892486572266},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/asru.2007.4430173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/6604616","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Data_Selection_for_Speech_Recognition/6604616","pdf_url":"https://figshare.com/articles/Data_Selection_for_Speech_Recognition/6604616","source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},{"id":"pmh:oai:repository.cmu.edu:compsci-2356","is_oa":false,"landing_page_url":"http://repository.cmu.edu/compsci/1357","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6604616","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.119.9853","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.119.9853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~yiwu/paper/asru07.pdf","raw_type":"text"},{"id":"doi:10.1184/r1/6604616.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6604616.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6604616","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Data_Selection_for_Speech_Recognition/6604616","pdf_url":"https://figshare.com/articles/Data_Selection_for_Speech_Recognition/6604616","source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2032020816.pdf","grobid_xml":"https://content.openalex.org/works/W2032020816.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W647193342","https://openalex.org/W1480376833","https://openalex.org/W1490760466","https://openalex.org/W1535702289","https://openalex.org/W1540371244","https://openalex.org/W1706091990","https://openalex.org/W1900116963","https://openalex.org/W1975113979","https://openalex.org/W1977286842","https://openalex.org/W2103592412","https://openalex.org/W2111702745","https://openalex.org/W2148712804","https://openalex.org/W2161482971","https://openalex.org/W2171761326","https://openalex.org/W2401172342","https://openalex.org/W2793863914","https://openalex.org/W3149836819"],"related_works":["https://openalex.org/W2393609567","https://openalex.org/W2369369044","https://openalex.org/W1503216044","https://openalex.org/W2354143083","https://openalex.org/W2372906645","https://openalex.org/W4319998713","https://openalex.org/W2366269494","https://openalex.org/W2353650902","https://openalex.org/W2347884623","https://openalex.org/W2361201432"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,58,70,76],"strategy":[4],"for":[5],"efficiently":[6],"selecting":[7],"informative":[8,60],"data":[9,20,48,63],"from":[10],"large":[11],"corpora":[12],"of":[13,26,62,75,80],"transcribed":[14],"speech.":[15],"We":[16],"propose":[17],"to":[18,23,40,56,69],"choose":[19],"uniformly":[21],"according":[22],"the":[24,41,83],"distribution":[25],"some":[27],"target":[28],"speech":[29],"unit":[30],"(phoneme,":[31],"word,":[32],"character,":[33],"etc).":[34],"In":[35],"our":[36,86],"experiment,":[37],"in":[38],"contrast":[39],"common":[42],"belief":[43],"that":[44,64,72],"\"there":[45],"is":[46,89],"no":[47],"like":[49],"more":[50],"data\",":[51],"we":[52],"found":[53],"it":[54],"possible":[55],"select":[57],"highly":[59],"subset":[61],"produces":[65],"recognition":[66],"performance":[67],"comparable":[68],"system":[71],"makes":[73],"use":[74],"much":[77],"larger":[78],"amount":[79],"data.":[81],"At":[82],"same":[84],"time,":[85],"selection":[87],"process":[88],"efficient":[90],"and":[91],"fast.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
