{"id":"https://openalex.org/W2015631279","doi":"https://doi.org/10.1109/msp.2012.2197156","title":"Large-Vocabulary Continuous Speech Recognition Systems: A Look at Some Recent Advances","display_name":"Large-Vocabulary Continuous Speech Recognition Systems: A Look at Some Recent Advances","publication_year":2012,"publication_date":"2012-10-19","ids":{"openalex":"https://openalex.org/W2015631279","doi":"https://doi.org/10.1109/msp.2012.2197156","mag":"2015631279"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2012.2197156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2012.2197156","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Thomas J Watson Research Center, Yorktown Heights, NY, US","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J Watson Research Center, Yorktown Heights, NY, US","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["National Cheng Kung University, Tainan, TW","Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University, Tainan, TW","institution_ids":["https://openalex.org/I91807558"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University , Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":21.3121,"has_fulltext":false,"cited_by_count":130,"citation_normalized_percentile":{"value":0.99487596,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"29","issue":"6","first_page":"18","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9891999959945679,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9886999726295471,"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":0.87235027551651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7825795412063599},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.7730318307876587},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6727975010871887},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5914234519004822},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.5075753927230835},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4838230013847351},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4777331054210663},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46154314279556274},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45924240350723267},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44065025448799133},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4130935072898865},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41179654002189636},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3655152916908264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35849320888519287},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.24330151081085205},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14007702469825745}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.87235027551651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7825795412063599},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.7730318307876587},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6727975010871887},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5914234519004822},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.5075753927230835},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4838230013847351},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4777331054210663},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46154314279556274},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45924240350723267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44065025448799133},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4130935072898865},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41179654002189636},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3655152916908264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35849320888519287},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.24330151081085205},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14007702469825745},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msp.2012.2197156","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2012.2197156","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":143,"referenced_works":["https://openalex.org/W13802415","https://openalex.org/W33139488","https://openalex.org/W34922426","https://openalex.org/W43454013","https://openalex.org/W72757270","https://openalex.org/W84880661","https://openalex.org/W89824565","https://openalex.org/W130324013","https://openalex.org/W153444084","https://openalex.org/W169377849","https://openalex.org/W173561343","https://openalex.org/W179875071","https://openalex.org/W1485038873","https://openalex.org/W1517381888","https://openalex.org/W1550447720","https://openalex.org/W1565453839","https://openalex.org/W1573570773","https://openalex.org/W1601795611","https://openalex.org/W1644652583","https://openalex.org/W1805340023","https://openalex.org/W1877570817","https://openalex.org/W1880262756","https://openalex.org/W1904457459","https://openalex.org/W1963783625","https://openalex.org/W1970689298","https://openalex.org/W1975113979","https://openalex.org/W1981706894","https://openalex.org/W1982309858","https://openalex.org/W1989705153","https://openalex.org/W1993561131","https://openalex.org/W1993882792","https://openalex.org/W1994396704","https://openalex.org/W1996903695","https://openalex.org/W2002342963","https://openalex.org/W2006701229","https://openalex.org/W2010556676","https://openalex.org/W2012897754","https://openalex.org/W2021396747","https://openalex.org/W2024539680","https://openalex.org/W2031284124","https://openalex.org/W2032210463","https://openalex.org/W2036912417","https://openalex.org/W2038288667","https://openalex.org/W2045036776","https://openalex.org/W2046932483","https://openalex.org/W2049633694","https://openalex.org/W2050971845","https://openalex.org/W2054755313","https://openalex.org/W2058216438","https://openalex.org/W2064203761","https://openalex.org/W2080400971","https://openalex.org/W2084514013","https://openalex.org/W2090861223","https://openalex.org/W2091544142","https://openalex.org/W2097003869","https://openalex.org/W2097560587","https://openalex.org/W2098318492","https://openalex.org/W2099424804","https://openalex.org/W2100474170","https://openalex.org/W2104448323","https://openalex.org/W2104663520","https://openalex.org/W2105885996","https://openalex.org/W2106615987","https://openalex.org/W2111479622","https://openalex.org/W2115407392","https://openalex.org/W2116047093","https://openalex.org/W2116361377","https://openalex.org/W2118186095","https://openalex.org/W2118595744","https://openalex.org/W2118714763","https://openalex.org/W2121227244","https://openalex.org/W2123876776","https://openalex.org/W2125234026","https://openalex.org/W2125436743","https://openalex.org/W2125610823","https://openalex.org/W2125838338","https://openalex.org/W2126033156","https://openalex.org/W2126415164","https://openalex.org/W2129703168","https://openalex.org/W2131033001","https://openalex.org/W2131034123","https://openalex.org/W2135346345","https://openalex.org/W2136922672","https://openalex.org/W2141212024","https://openalex.org/W2142084376","https://openalex.org/W2142499181","https://openalex.org/W2142825941","https://openalex.org/W2144049961","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150286230","https://openalex.org/W2150907703","https://openalex.org/W2154099718","https://openalex.org/W2155117693","https://openalex.org/W2158195707","https://openalex.org/W2158289097","https://openalex.org/W2158420521","https://openalex.org/W2159112514","https://openalex.org/W2159382562","https://openalex.org/W2160237783","https://openalex.org/W2160815625","https://openalex.org/W2161513525","https://openalex.org/W2163426739","https://openalex.org/W2164115090","https://openalex.org/W2164225659","https://openalex.org/W2164931619","https://openalex.org/W2165108269","https://openalex.org/W2165712214","https://openalex.org/W2167270514","https://openalex.org/W2394932179","https://openalex.org/W2594610113","https://openalex.org/W2917348560","https://openalex.org/W2998704965","https://openalex.org/W4231510805","https://openalex.org/W4285719527","https://openalex.org/W4299987818","https://openalex.org/W6600533907","https://openalex.org/W6601376335","https://openalex.org/W6601431124","https://openalex.org/W6602923018","https://openalex.org/W6603374476","https://openalex.org/W6603662750","https://openalex.org/W6605298800","https://openalex.org/W6606255316","https://openalex.org/W6607023580","https://openalex.org/W6607114211","https://openalex.org/W6607333740","https://openalex.org/W6629029613","https://openalex.org/W6630893669","https://openalex.org/W6633818701","https://openalex.org/W6634340323","https://openalex.org/W6636890138","https://openalex.org/W6638196668","https://openalex.org/W6639619044","https://openalex.org/W6652122831","https://openalex.org/W6674447887","https://openalex.org/W6678457041","https://openalex.org/W6678800364","https://openalex.org/W6680532216","https://openalex.org/W6682398751","https://openalex.org/W6682871038","https://openalex.org/W6683547160","https://openalex.org/W6711962127"],"related_works":["https://openalex.org/W2355709873","https://openalex.org/W2337605147","https://openalex.org/W2036933852","https://openalex.org/W4388404911","https://openalex.org/W134179020","https://openalex.org/W1587401114","https://openalex.org/W2184127972","https://openalex.org/W2105439218","https://openalex.org/W4312668661","https://openalex.org/W3120523696"],"abstract_inverted_index":{"Over":[0],"the":[1,12,24,88,98,111,117],"past":[2],"decade":[3],"or":[4,138],"so,":[5],"several":[6],"advances":[7],"have":[8],"been":[9],"made":[10],"to":[11,23,37,65,79,94,146,160],"design":[13],"of":[14,72,90,97,101,119,180,182,186,188],"modern":[15,102],"large":[16],"vocabulary":[17],"continuous":[18],"speech":[19,51,59,121,183],"recognition":[20,122,149],"(LVCSR)":[21],"systems":[22,36,74,145,156],"point":[25],"where":[26],"their":[27],"application":[28],"has":[29,85],"broadened":[30],"from":[31,125],"early":[32],"speaker":[33],"dependent":[34],"dictation":[35],"speaker-independent":[38],"automatic":[39],"broadcast":[40],"news":[41],"transcription":[42],"and":[43,46,57,61,87,114,135,163,166,184],"indexing,":[44],"lectures":[45],"meetings":[47],"transcription,":[48,52],"conversational":[49],"telephone":[50],"open-domain":[53],"voice":[54],"search,":[55],"medical":[56],"legal":[58],"recognition,":[60],"call":[62],"center":[63],"applications,":[64],"name":[66],"a":[67],"few.":[68],"The":[69],"commercial":[70,112],"success":[71,113],"these":[73],"is":[75,93,123,152],"an":[76],"impressive":[77],"testimony":[78],"how":[80],"far":[81,124],"research":[82],"in":[83],"LVCSR":[84,155],"come,":[86],"aim":[89],"this":[91],"article":[92],"describe":[95],"some":[96],"technological":[99],"underpinnings":[100],"systems.":[103],"It":[104],"must":[105],"be":[106],"said,":[107],"however,":[108],"that,":[109],"despite":[110,175],"widespread":[115],"adoption,":[116],"problem":[118],"large-vocabulary":[120],"being":[126,176],"solved:":[127],"background":[128],"noise,":[129],"channel":[130],"distortions,":[131],"foreign":[132],"accents,":[133],"casual":[134],"disfluent":[136],"speech,":[137],"unexpected":[139],"topic":[140],"change":[141],"can":[142],"cause":[143],"automated":[144],"make":[147],"egregious":[148],"errors.":[150],"This":[151],"because":[153],"current":[154],"are":[157],"not":[158],"robust":[159],"mismatched":[161],"training":[162],"test":[164],"conditions":[165],"cannot":[167],"handle":[168],"context":[169],"as":[170,172],"well":[171],"human":[173],"listeners":[174],"trained":[177],"on":[178],"thousands":[179],"hours":[181],"billions":[185],"words":[187],"text.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":16},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}