{"id":"https://openalex.org/W2065579212","doi":"https://doi.org/10.1109/bigdata.2014.7004349","title":"Scalable big data computing for the personalization of machine learned models and its application to automatic speech recognition service","display_name":"Scalable big data computing for the personalization of machine learned models and its application to automatic speech recognition service","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2065579212","doi":"https://doi.org/10.1109/bigdata.2014.7004349","mag":"2065579212"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2014.7004349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5075603376","display_name":"Jong Hoon Ahnn","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jong Hoon Ahnn","raw_affiliation_strings":["Cloud Research Lab, Samsung Research America, Silicon Valley","Cloud Research Lab, Samsung Research America - Silicon Valley"],"affiliations":[{"raw_affiliation_string":"Cloud Research Lab, Samsung Research America, Silicon Valley","institution_ids":["https://openalex.org/I4210101778"]},{"raw_affiliation_string":"Cloud Research Lab, Samsung Research America - Silicon Valley","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075603376"],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":0.6896,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74951508,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8889663219451904},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6549100279808044},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6249321699142456},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6056416630744934},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5022351741790771},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4461626410484314},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4369242191314697},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41885778307914734},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4119570851325989},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3867139220237732},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3345867097377777},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2616746127605438},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23865845799446106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8889663219451904},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6549100279808044},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6249321699142456},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6056416630744934},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5022351741790771},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4461626410484314},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4369242191314697},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41885778307914734},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4119570851325989},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3867139220237732},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3345867097377777},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2616746127605438},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23865845799446106},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2014.7004349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2014.7004349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.6499999761581421,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1236737278","https://openalex.org/W1545714674","https://openalex.org/W1735711190","https://openalex.org/W2096125134","https://openalex.org/W2138234674","https://openalex.org/W2140509629","https://openalex.org/W2167466454","https://openalex.org/W2170876481","https://openalex.org/W6632512953","https://openalex.org/W6637464354","https://openalex.org/W6685391744"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2910064364","https://openalex.org/W4200136508","https://openalex.org/W2109940557"],"abstract_inverted_index":{"We":[0,46,108,142,161,200,236],"observe":[1],"that":[2,50],"the":[3,42,118,144,205,213,219,225,231],"recent":[4],"advances":[5,63],"in":[6,34,58,64,74,91,137],"big":[7,67,119],"data":[8,54,68,120,244],"computing":[9],"have":[10],"empowered":[11],"model-based":[12],"services":[13,73,129,259],"such":[14,130],"as":[15,131],"speech":[16],"recognition,":[17,19],"face":[18],"context-aware":[20],"service,":[21],"and":[22,55,66,97,112,154,181,222,243,247,264],"many":[23,75],"other":[24,220],"services.":[25,78],"Various":[26],"sources":[27],"of":[28,44,77,104,146,158,166,207,215,234],"user's":[29],"logs":[30],"can":[31,51],"be":[32],"utilized":[33],"remodeling":[35],"or":[36,177],"adapting":[37],"existing":[38],"models":[39],"to":[40,127,211,252,260],"improve":[41],"quality":[43],"service.":[45],"propose":[47,109],"a":[48,59,93,110,138,202],"system":[49,115,193],"support":[52,262],"store/retrieve":[53],"process":[56],"them":[57],"scalable":[60,113],"manner.":[61],"Recently":[62],"ASR":[65,114],"technologies":[69],"drive":[70],"more":[71],"personalized":[72,94,111,125,208],"areas":[76],"A":[79],"speaker":[80,147],"adaptation":[81,148],"is":[82],"one":[83,216],"good":[84],"example":[85],"which":[86,122],"requires":[87],"huge":[88],"computation":[89],"cost":[90,206],"creating":[92],"acoustic":[95],"model":[96,100,209],"corresponding":[98],"language":[99],"over":[101],"100s":[102],"millions":[103],"Samsung":[105],"product":[106],"users.":[107],"powered":[116],"by":[117,169],"infrastructure":[121],"brings":[123],"data-driven":[124],"opportunities":[126],"voice-enabled":[128,134,258],"voice-to-text":[132],"transcriber,":[133],"web":[135],"search":[136],"peta":[139],"bytes":[140],"scale.":[141],"verify":[143],"feasibility":[145],"based":[149],"on":[150,174],"107":[151],"testers'":[152],"recordings":[153],"obtain":[155],"about":[156],"10%":[157],"recognition":[159],"accuracy.":[160],"study":[162],"an":[163],"optimal":[164],"set":[165],"execution":[167,228],"environments":[168],"executing":[170],"jobs":[171],"running":[172],"either":[173],"Hadoop":[175,178],"1":[176],"2":[179],"cluster,":[180,221],"move":[182],"forward":[183],"performance":[184,250],"optimization":[185],"strategies:":[186],"workflow":[187],"compaction,":[188],"file":[189,192,198],"compression,":[190],"best":[191],"selection":[194],"among":[195],"several":[196],"distributed":[197],"systems.":[199],"devise":[201],"metric":[203],"for":[204,230,257],"creation":[210],"compare":[212],"efficiency":[214],"cluster":[217],"with":[218],"it":[223],"provides":[224],"estimated":[226],"total":[227],"time":[229],"given":[232],"number":[233],"machines.":[235],"finally":[237],"introduce":[238],"our":[239],"in-house":[240],"object":[241],"storage":[242,245],"design,":[246],"their":[248],"high":[249],"compared":[251],"state-of-the":[253],"art":[254],"systems,":[255],"optimized":[256],"effectively":[261],"small":[263],"large":[265],"files.":[266]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}