{"id":"https://openalex.org/W3137678309","doi":"https://doi.org/10.1109/bigdata50022.2020.9378438","title":"A Study of Spoken Audio Processing using Machine Learning for Libraries, Archives and Museums (LAM)","display_name":"A Study of Spoken Audio Processing using Machine Learning for Libraries, Archives and Museums (LAM)","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3137678309","doi":"https://doi.org/10.1109/bigdata50022.2020.9378438","mag":"3137678309"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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/A5101883722","display_name":"Weijia Xu","orcid":"https://orcid.org/0000-0002-5134-6381"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Weijia Xu","raw_affiliation_strings":["Texas Advanced Computing Center, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, University of Texas at Austin, Austin, Texas, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078797277","display_name":"Mar\u00eda Esteva","orcid":"https://orcid.org/0000-0001-6204-4517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Esteva","raw_affiliation_strings":["Texas Advanced Computing Center, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, University of Texas at Austin, Austin, Texas, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010080547","display_name":"Peter Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Cui","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040568201","display_name":"Eugene Castillo","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Castillo","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031190010","display_name":"Kewen Wang","orcid":"https://orcid.org/0000-0002-0542-3761"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kewen Wang","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005553832","display_name":"H. Kenneth Hopkins","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanna-Robbins Hopkins","raw_affiliation_strings":["Department of English, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Department of English, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087287236","display_name":"Tanya Clement","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanya Clement","raw_affiliation_strings":["Department of English, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Department of English, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078405142","display_name":"Aaron Choate","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aaron Choate","raw_affiliation_strings":["University of Texas Libraries, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"University of Texas Libraries, University of Texas at Austin, Austin, Texas, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057218817","display_name":"Ruizhu Huang","orcid":"https://orcid.org/0000-0003-3285-1945"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruizhu Huang","raw_affiliation_strings":["Texas Advanced Computing Center, University of Texas at Austin, Austin, Texas, USA"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, University of Texas at Austin, Austin, Texas, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101883722"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48406847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"1939","last_page":"1948"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9922999739646912,"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/metadata","display_name":"Metadata","score":0.8854542970657349},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.8376936316490173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8376786112785339},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6944835782051086},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6135624051094055},{"id":"https://openalex.org/keywords/sync","display_name":"sync","score":0.6083766222000122},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.4505883753299713},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.441888689994812},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4236983358860016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3220096230506897},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23331376910209656}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8854542970657349},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.8376936316490173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8376786112785339},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6944835782051086},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6135624051094055},{"id":"https://openalex.org/C3913047","wikidata":"https://www.wikidata.org/wiki/Q1956265","display_name":"sync","level":3,"score":0.6083766222000122},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.4505883753299713},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.441888689994812},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4236983358860016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3220096230506897},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23331376910209656},{"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},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W118756463","https://openalex.org/W327991062","https://openalex.org/W1532325895","https://openalex.org/W1551709509","https://openalex.org/W1600744878","https://openalex.org/W1677683623","https://openalex.org/W1922655562","https://openalex.org/W2061809273","https://openalex.org/W2077236205","https://openalex.org/W2080213370","https://openalex.org/W2097207027","https://openalex.org/W2112739286","https://openalex.org/W2117671523","https://openalex.org/W2136743277","https://openalex.org/W2143612262","https://openalex.org/W2145565586","https://openalex.org/W2147229751","https://openalex.org/W2147627917","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2169189000","https://openalex.org/W2172256532","https://openalex.org/W2191333630","https://openalex.org/W2193413348","https://openalex.org/W2277583061","https://openalex.org/W2293634267","https://openalex.org/W2309460698","https://openalex.org/W2474251382","https://openalex.org/W2587195211","https://openalex.org/W2790357563","https://openalex.org/W2802642435","https://openalex.org/W2802787326","https://openalex.org/W2820734700","https://openalex.org/W2894054914","https://openalex.org/W2896457183","https://openalex.org/W2913768775","https://openalex.org/W2953039584","https://openalex.org/W2953356739","https://openalex.org/W2953384591","https://openalex.org/W2964165818","https://openalex.org/W2993258659","https://openalex.org/W3133806040","https://openalex.org/W4213009331","https://openalex.org/W4235637372","https://openalex.org/W4294152847","https://openalex.org/W6640090968","https://openalex.org/W6681345128","https://openalex.org/W6681762807","https://openalex.org/W6687566353","https://openalex.org/W6713134421","https://openalex.org/W6751678649","https://openalex.org/W6755086743","https://openalex.org/W6755207826"],"related_works":["https://openalex.org/W2063547430","https://openalex.org/W2524993630","https://openalex.org/W2607244263","https://openalex.org/W2234430299","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W1831690014","https://openalex.org/W1561022130"],"abstract_inverted_index":{"As":[0],"the":[1,20,34,84,135,139,145,157,209,216,229],"need":[2,21],"to":[3,6,22,33,45,100,162,172,176,192,236,239],"provide":[4,185],"access":[5],"spoken":[7],"word":[8],"audio":[9,29,35,71,112],"collections":[10,72],"in":[11,73,194],"libraries,":[12],"archives,":[13],"and":[14,26,40,62,92,138,150,182,184,215],"museums":[15],"(LAM)":[16],"increases,":[17],"so":[18],"does":[19],"process":[23],"them":[24],"efficiently":[25],"consistently.":[27],"Traditionally,":[28],"processing":[30,69],"involves":[31],"listening":[32],"files,":[36],"conducting":[37],"manual":[38],"transcription,":[39],"applying":[41],"controlled":[42],"subject":[43],"terms":[44],"describe":[46,101],"them.":[47,104],"This":[48],"workflow":[49,153,189],"takes":[50],"significant":[51],"time":[52],"with":[53,78,196],"each":[54,102],"recording.":[55],"In":[56],"this":[57,188],"study,":[58],"we":[59,125,241],"investigate":[60],"if":[61],"how":[63],"machine":[64],"learning":[65],"(ML)":[66],"can":[67],"facilitate":[68],"of":[70,87,103,208,218,231],"a":[74,206],"manner":[75],"that":[76,96,219],"corresponds":[77],"LAM":[79,167,197],"best":[80],"practices.":[81],"We":[82],"use":[83],"StoryCorps":[85],"collection":[86],"oral":[88],"histories":[89],"\"Las":[90],"Historias,\"":[91],"fixed":[93],"subjects":[94],"(metadata)":[95],"are":[97,114,147],"manually":[98,233],"assigned":[99,234],"Our":[105],"methodology":[106],"has":[107,202],"two":[108,118],"main":[109],"phases.":[110],"First,":[111],"files":[113],"automatically":[115],"transcribed":[116],"using":[117,134,232],"automatic":[119],"speech":[120],"recognition":[121],"(ASR)":[122],"methods.":[123],"Next,":[124],"build":[126,237],"different":[127,212],"supervised":[128],"ML":[129,174],"models":[130],"for":[131,166,245],"label":[132,222],"prediction":[133,223],"transcription":[136,213],"data":[137],"existing":[140],"metadata.":[141],"Throughout":[142],"these":[143],"phases":[144],"results":[146],"analyzed":[148],"quantitatively":[149],"qualitatively.":[151],"The":[152,200,225],"is":[154],"implemented":[155],"within":[156],"flexible":[158],"web":[159],"framework":[160],"IDOLS":[161],"lower":[163],"technical":[164],"barriers":[165],"professionals.":[168],"By":[169],"allowing":[170],"users":[171,191],"submit":[173],"jobs":[175],"supercomputers,":[177],"reproduce":[178],"workflows,":[179],"change":[180],"configurations,":[181],"view":[183],"feedback":[186],"transparently,":[187],"allows":[190],"be":[193],"sync":[195],"professional":[198],"values.":[199],"study":[201,226],"several":[203],"outcomes":[204],"including":[205],"comparison":[207],"quality":[210,220],"between":[211],"methods":[214],"impact":[217],"on":[221],"accuracy.":[224],"also":[227],"unveiled":[228],"limitations":[230],"metadata":[235],"models,":[238],"which":[240],"suggest":[242],"alternate":[243],"strategies":[244],"building":[246],"successful":[247],"training":[248],"data.":[249]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}