{"id":"https://openalex.org/W2007264691","doi":"https://doi.org/10.1109/icassp.2014.6854210","title":"Multi-stream combination for LVCSR and keyword search on GPU-accelerated platforms","display_name":"Multi-stream combination for LVCSR and keyword search on GPU-accelerated platforms","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2007264691","doi":"https://doi.org/10.1109/icassp.2014.6854210","mag":"2007264691"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854210","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 Acoustics, Speech and Signal Processing (ICASSP)","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/A5022491076","display_name":"Wonkyum Lee","orcid":null},"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":true,"raw_author_name":"Wonkyum Lee","raw_affiliation_strings":["Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA, USA","Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101991949","display_name":"Jungsuk Kim","orcid":"https://orcid.org/0000-0001-5866-465X"},"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":"Jungsuk Kim","raw_affiliation_strings":["Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA, USA","Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","orcid":null},"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":"Ian Lane","raw_affiliation_strings":["Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA, USA","Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Electrical and Computer Engineering, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Electr. & Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022491076"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.636,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8687893,"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":"3296","last_page":"3300"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8520889282226562},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6018945574760437},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5943466424942017},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5780856013298035},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.46730613708496094},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4435109794139862},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.41764071583747864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40198880434036255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3675752878189087},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.367168128490448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8520889282226562},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6018945574760437},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5943466424942017},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5780856013298035},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.46730613708496094},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4435109794139862},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.41764071583747864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40198880434036255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3675752878189087},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.367168128490448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854210","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 Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W34089377","https://openalex.org/W114504754","https://openalex.org/W173561343","https://openalex.org/W1904457459","https://openalex.org/W1951971685","https://openalex.org/W1974205368","https://openalex.org/W2037102844","https://openalex.org/W2046932483","https://openalex.org/W2078396654","https://openalex.org/W2103635001","https://openalex.org/W2110755351","https://openalex.org/W2132991150","https://openalex.org/W2136105097","https://openalex.org/W2144121180","https://openalex.org/W2160688560","https://openalex.org/W2397534874","https://openalex.org/W2594610113","https://openalex.org/W6607114211","https://openalex.org/W6669996083"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2121652828","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"In":[0],"this":[1,40],"paper,":[2],"we":[3,53,158],"explore":[4],"methods":[5],"for":[6,21,47,148,175],"system":[7],"combination":[8,103,135],"of":[9,91,166],"acoustic":[10,49,60,85,177],"models":[11,61],"having":[12],"different":[13,63],"features,":[14],"modeling":[15],"approaches":[16],"and":[17,24,37,44,99],"phonetic":[18,64,155,167],"decision":[19,156,168],"trees":[20,65],"speech":[22,106,120],"recognition":[23,107,121],"keyword":[25,150],"search.":[26],"We":[27,87],"introduce":[28,54],"a":[29,55,67,137],"Graphic":[30],"Processing":[31],"Unit":[32],"(GPU)-accelerated":[33],"lattice":[34,78],"generation":[35,79],"method":[36,57],"show":[38],"that":[39,101],"architecture":[41],"is":[42],"efficient":[43,173],"well":[45],"suited":[46],"multi-stream":[48,93,102,134],"model":[50],"combination.":[51],"Additionally,":[52,129],"novel":[56],"to":[58,80,95,115,124,146],"combine":[59],"with":[62],"into":[66],"single":[68,126],"fully":[69],"composed":[70],"HMM":[71],"state":[72],"level":[73],"(H-level)":[74],"WFST":[75],"network":[76],"allowing":[77],"be":[81],"performed":[82],"using":[83,171],"diverse":[84],"models.":[86],"evaluate":[88],"the":[89,125,149,164],"performance":[90],"our":[92],"approach":[94],"three":[96],"standard":[97],"techniques":[98],"observe":[100],"obtains":[104],"higher":[105,139],"accuracy":[108,122],"than":[109],"Lattice":[110],"Combination":[111],"or":[112],"ROVER":[113],"(up":[114],"5.5%":[116],"relative":[117],"improvement":[118],"in":[119],"compared":[123,145],"best":[127],"model).":[128],"at":[130],"an":[131],"equivalent":[132],"runtime,":[133],"obtained":[136,159],"15%":[138],"Average":[140],"Term":[141],"Weighted":[142],"Value":[143],"(ATWV)":[144],"CombMNZ":[147],"search":[151],"task.":[152],"By":[153],"combining":[154],"tree,":[157],"gain":[160],"(WER":[161],"reduction)":[162],"from":[163],"diversity":[165],"tree":[169,174],"by":[170],"more":[172],"each":[176],"model.":[178]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"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"}