{"id":"https://openalex.org/W2773095876","doi":"https://doi.org/10.1109/icassp.2018.8461935","title":"Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition","display_name":"Building Competitive Direct Acoustics-to-Word Models for English Conversational Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2773095876","doi":"https://doi.org/10.1109/icassp.2018.8461935","mag":"2773095876"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.03133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"institutions":[{"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":"Kartik Audhkhasi","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, New York","IBM, T.J. Watson Research Center, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"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":"Brian Kingsbury","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, New York","IBM, T.J. Watson Research Center, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"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":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, New York","IBM, T.J. Watson Research Center, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"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 T. J. Watson Research Center, Yorktown Heights, New York","IBM, T.J. Watson Research Center, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"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":"Michael Picheny","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, New York","IBM, T.J. Watson Research Center, Yorktown Heights, New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM, T.J. Watson Research Center, Yorktown Heights, New York","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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":0.8282345533370972},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7437742352485657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7248826026916504},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7072299718856812},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6330908536911011},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.560826301574707},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5513550639152527},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5507057905197144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5004310607910156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4847102165222168},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4605587422847748},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.43487071990966797},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4268917441368103},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42430272698402405},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.4226863980293274},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.263272225856781},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13819512724876404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282345533370972},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7437742352485657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7248826026916504},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7072299718856812},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6330908536911011},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.560826301574707},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5513550639152527},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5507057905197144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5004310607910156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4847102165222168},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4605587422847748},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.43487071990966797},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4268917441368103},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42430272698402405},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.4226863980293274},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.263272225856781},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13819512724876404},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8461935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461935","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1712.03133","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03133","pdf_url":"https://arxiv.org/pdf/1712.03133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2773095876","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1712.03133.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1712.03133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1712.03133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.03133","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03133","pdf_url":"https://arxiv.org/pdf/1712.03133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2773095876.pdf","grobid_xml":"https://content.openalex.org/works/W2773095876.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W81527949","https://openalex.org/W183136171","https://openalex.org/W1508165687","https://openalex.org/W1736701665","https://openalex.org/W2058641082","https://openalex.org/W2058829475","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2250539671","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2395416438","https://openalex.org/W2514741789","https://openalex.org/W2519224033","https://openalex.org/W2533523411","https://openalex.org/W2545177271","https://openalex.org/W2559302184","https://openalex.org/W2594856242","https://openalex.org/W2597757402","https://openalex.org/W2604132379","https://openalex.org/W2739427748","https://openalex.org/W2746192915","https://openalex.org/W2952288254","https://openalex.org/W2953291251","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963920996","https://openalex.org/W2964308564","https://openalex.org/W6607418263","https://openalex.org/W6629052376","https://openalex.org/W6631943919","https://openalex.org/W6664793490","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6687566353","https://openalex.org/W6691431627","https://openalex.org/W6696904280","https://openalex.org/W6727193155","https://openalex.org/W6734588641"],"related_works":["https://openalex.org/W2963070863","https://openalex.org/W2597757402","https://openalex.org/W2127141656","https://openalex.org/W2951327905","https://openalex.org/W2952613254","https://openalex.org/W2916685081","https://openalex.org/W2187090609","https://openalex.org/W2095734449","https://openalex.org/W68711274","https://openalex.org/W125614575","https://openalex.org/W2293858598","https://openalex.org/W2151058131","https://openalex.org/W2802184895","https://openalex.org/W2964309797","https://openalex.org/W2035789797","https://openalex.org/W2184468823","https://openalex.org/W2056590938","https://openalex.org/W2097809450","https://openalex.org/W2940322076","https://openalex.org/W108809533"],"abstract_inverted_index":{"Direct":[0],"acoustics-to-word":[1],"(A2W)":[2],"models":[3,20,34,54,62],"in":[4,70,190],"the":[5,87,123,145,149,166,179,191],"end-to-end":[6],"paradigm":[7],"have":[8,144],"received":[9],"increasing":[10],"attention":[11],"compared":[12],"to":[13,72,75,97,163,178],"conventional":[14,76],"subword":[15],"based":[16,112],"automatic":[17],"speech":[18,38],"recognition":[19],"using":[21,86],"phones,":[22],"characters,":[23],"or":[24,44,131,196],"context-dependent":[25],"hidden":[26],"Markov":[27],"model":[28,101,137,151,160,173],"states.":[29],"This":[30,92,172],"is":[31,107],"because":[32],"A2W":[33,61,100,150,159],"recognize":[35,170],"words":[36,194],"from":[37],"without":[39,128],"any":[40,129],"decoder,":[41],"pronunciation":[42],"lexicon,":[43],"externally-trained":[45],"language":[46,132],"model,":[47],"making":[48,186],"training":[49,68,139],"and":[50,106,142,168],"decoding":[51],"with":[52,109],"such":[53],"simple.":[55],"Prior":[56],"work":[57,79],"has":[58],"shown":[59],"that":[60,102,136,161],"require":[63],"orders":[64],"of":[65,120,182,193],"magnitude":[66],"more":[67],"data":[69,90,140],"order":[71],"perform":[73],"comparably":[74],"models.":[77,113],"Our":[78],"also":[80],"showed":[81],"this":[82,104],"accuracy":[83],"gap":[84,105],"when":[85],"English":[88],"Switchboard-Fisher":[89],"set.":[91],"paper":[93],"describes":[94],"a":[95,116,156,175],"recipe":[96],"train":[98],"an":[99],"closes":[103],"at-par":[108],"state-of-the-art":[110],"sub-word":[111],"We":[114,134],"achieve":[115],"word":[117,167,184],"error":[118],"rate":[119],"8.8.8%/13.9%":[121],"on":[122,148],"Hub5-2000":[124],"Switchboard/CallHome":[125],"test":[126],"sets":[127],"decoder":[130],"model.":[133],"find":[135],"initialization,":[138],"order,":[141],"regularization":[143],"most":[146],"impact":[147],"performance.":[152],"Next,":[153],"we":[154],"present":[155],"joint":[157],"word-character":[158],"learns":[162],"first":[164],"spell":[165],"then":[169],"it.":[171],"provides":[174],"rich":[176],"output":[177],"user":[180],"instead":[181],"simple":[183],"hypotheses,":[185],"it":[187],"especially":[188],"useful":[189],"case":[192],"unseen":[195],"rarely-seen":[197],"during":[198],"training.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}