{"id":"https://openalex.org/W2290554209","doi":"https://doi.org/10.1109/asru.2015.7404788","title":"Improving data selection for low-resource STT and KWS","display_name":"Improving data selection for low-resource STT and KWS","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2290554209","doi":"https://doi.org/10.1109/asru.2015.7404788","mag":"2290554209"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5045988326","display_name":"Thiago Fraga-Silva","orcid":"https://orcid.org/0009-0001-7928-8929"},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thiago Fraga-Silva","raw_affiliation_strings":["Vocapia Research, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, France","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["Vocapia Research, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, France","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["CNRS/LIMSI, Spoken Language Processing Group, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS/LIMSI, Spoken Language Processing Group, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["CNRS/LIMSI, Spoken Language Processing Group, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS/LIMSI, Spoken Language Processing Group, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044153954","display_name":"Viet-Bac Le","orcid":null},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Viet-Bac Le","raw_affiliation_strings":["Vocapia Research, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, France","institution_ids":["https://openalex.org/I99555447"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017942351","display_name":"Abdel Messaoudi","orcid":null},"institutions":[{"id":"https://openalex.org/I99555447","display_name":"Vocapia Research (France)","ror":"https://ror.org/00606js28","country_code":"FR","type":"company","lineage":["https://openalex.org/I99555447"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Abdel Messaoudi","raw_affiliation_strings":["Vocapia Research, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vocapia Research, France","institution_ids":["https://openalex.org/I99555447"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.823,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74955048,"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":"153","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9957000017166138,"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":0.9868000149726868,"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":0.8148726224899292},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.7170809507369995},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6411827802658081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5576295852661133},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49331870675086975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4871823191642761},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43500617146492004},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42557328939437866},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41768014430999756},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4128972291946411},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37500056624412537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8148726224899292},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7170809507369995},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6411827802658081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5576295852661133},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49331870675086975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4871823191642761},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43500617146492004},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42557328939437866},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41768014430999756},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4128972291946411},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37500056624412537},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404788","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404788","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W228764207","https://openalex.org/W350664472","https://openalex.org/W1509837333","https://openalex.org/W1555037511","https://openalex.org/W1604771987","https://openalex.org/W1965842648","https://openalex.org/W1993799394","https://openalex.org/W2016243284","https://openalex.org/W2032020816","https://openalex.org/W2052274902","https://openalex.org/W2053625667","https://openalex.org/W2059019626","https://openalex.org/W2091267617","https://openalex.org/W2091746061","https://openalex.org/W2106440210","https://openalex.org/W2117278770","https://openalex.org/W2117590177","https://openalex.org/W2120173366","https://openalex.org/W2292087804","https://openalex.org/W2294722231","https://openalex.org/W2397766809","https://openalex.org/W2403657120","https://openalex.org/W2406226915","https://openalex.org/W2407922671","https://openalex.org/W2442329935","https://openalex.org/W2594610113","https://openalex.org/W3007258144","https://openalex.org/W4285719527","https://openalex.org/W4300061183","https://openalex.org/W6608930086","https://openalex.org/W6611815725","https://openalex.org/W6630710561","https://openalex.org/W6635896687","https://openalex.org/W6658485743","https://openalex.org/W6677328538","https://openalex.org/W6677717300","https://openalex.org/W6696449567","https://openalex.org/W6712476315","https://openalex.org/W6713511519","https://openalex.org/W6713986472","https://openalex.org/W6714027799","https://openalex.org/W6718561954","https://openalex.org/W6773633977"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"This":[0,111],"paper":[1],"extends":[2],"recent":[3],"research":[4],"on":[5],"training":[6,52],"data":[7,53,118],"selection":[8,35,100,108,137],"for":[9,31,131],"speech":[10],"transcription":[11],"and":[12,104],"keyword":[13],"spotting":[14],"system":[15,46],"development.":[16],"Selection":[17],"techniques":[18],"were":[19,37,61,95,121],"explored":[20],"in":[21,75,123,146],"the":[22,25,40,58,69,80,124,132,142,147],"context":[23],"of":[24,42,57,71,79,82,99],"IARPA-Babel":[26],"Active":[27],"Learning":[28],"(AL)":[29],"task":[30],"6":[32,133],"languages.":[33,134],"Different":[34],"criteria":[36,101],"considered":[38],"with":[39],"goal":[41],"improving":[43],"over":[44],"a":[45,49,105],"built":[47],"using":[48,116],"pre-defined":[50],"3-hour":[51],"set.":[54],"Four":[55],"variants":[56],"entropy-based":[59],"criterion":[60],"explored:":[62],"words,":[63],"triphones,":[64],"phones":[65],"as":[66,68,86,88],"well":[67,87],"use":[70],"HMM-states":[72,83],"previously":[73],"introduced":[74],"[4].":[76],"The":[77,97,135],"influence":[78],"number":[81],"was":[84,102,113,138],"assessed":[85,115],"whether":[89],"automatic":[90],"or":[91],"manual":[92],"reference":[93],"transcripts":[94],"used.":[96],"combination":[98],"investigated,":[103],"novel":[106],"multi-stage":[107,136],"method":[109,112],"proposed.":[110],"also":[114,139],"larger":[117],"sets":[119],"than":[120],"permitted":[122],"Babel":[125],"AL":[126],"task.":[127],"Results":[128],"are":[129],"reported":[130],"applied":[140],"to":[141],"surprise":[143],"language":[144],"(Swahili)":[145],"NIST":[148],"OpenKWS":[149],"2015":[150],"evaluation.":[151]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}