{"id":"https://openalex.org/W2114016253","doi":"https://doi.org/10.1109/icassp.2009.4960445","title":"Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling","display_name":"Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2114016253","doi":"https://doi.org/10.1109/icassp.2009.4960445","mag":"2114016253"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"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":true,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"[IBM T.J. Watson Research Center, Yorktown Heights, NY 10598, USA]","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003725957"],"corresponding_institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":238,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3761","last_page":"3764"},"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.798818826675415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617543935775757},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.688990592956543},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6779882907867432},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6517945528030396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.576505184173584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239824652671814},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5029141306877136},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4745534062385559},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46557873487472534},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.44535380601882935},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.44153428077697754},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2194390892982483}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.798818826675415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617543935775757},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.688990592956543},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6779882907867432},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6517945528030396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.576505184173584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239824652671814},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5029141306877136},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4745534062385559},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46557873487472534},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.44535380601882935},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.44153428077697754},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2194390892982483},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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/icassp.2009.4960445","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960445","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W14913773","https://openalex.org/W21683646","https://openalex.org/W38527073","https://openalex.org/W1515149227","https://openalex.org/W1877570817","https://openalex.org/W2019125718","https://openalex.org/W2100772283","https://openalex.org/W2125234026","https://openalex.org/W2134756243","https://openalex.org/W2134900903","https://openalex.org/W2147467930","https://openalex.org/W2150907703","https://openalex.org/W2154887136","https://openalex.org/W2157749010","https://openalex.org/W2160355390","https://openalex.org/W2165712214","https://openalex.org/W2395140404","https://openalex.org/W3149335959","https://openalex.org/W6600588093","https://openalex.org/W6601546718","https://openalex.org/W6681920845","https://openalex.org/W6711851458"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2032826752"],"abstract_inverted_index":{"Acoustic":[0],"models":[1,56],"used":[2],"in":[3,85],"hidden":[4],"Markov":[5],"model/neural-network":[6],"(HMM/NN)":[7],"speech":[8,47],"recognition":[9,48],"systems":[10,25],"are":[11,26,42],"usually":[12],"trained":[13,28,59,100,126],"with":[14,60,97,127],"a":[15,81,108],"frame-based":[16],"cross-entropy":[17],"error":[18,36,110,137],"criterion.":[19],"In":[20],"contrast,":[21],"Gaussian":[22,75],"mixture":[23,76],"HMM":[24],"discriminatively":[27],"using":[29,64,80],"sequence-based":[30],"criteria,":[31],"such":[32],"as":[33],"minimum":[34,130],"phone":[35],"or":[37],"maximum":[38],"mutual":[39],"information,":[40],"that":[41,53,70,79],"more":[43],"directly":[44],"related":[45],"to":[46,88],"accuracy.":[49],"This":[50],"paper":[51],"demonstrates":[52],"neural-network":[54],"acoustic":[55,95],"can":[57],"be":[58],"sequence":[61,82],"classification":[62,83],"criteria":[63],"exactly":[65],"the":[66,115,128,134],"same":[67],"lattice-based":[68],"methods":[69],"have":[71],"been":[72],"developed":[73],"for":[74],"HMMs,":[77],"and":[78],"criterion":[84],"training":[86],"leads":[87],"considerably":[89],"better":[90],"performance.":[91],"A":[92],"neural":[93],"network":[94],"model":[96,124],"153K":[98],"weights":[99],"on":[101,114],"50":[102],"hours":[103],"of":[104,112],"broadcast":[105,118],"news":[106,119],"has":[107],"word":[109,136],"rate":[111,138],"34.0%":[113],"rt04":[116,135],"English":[117],"test":[120],"set.":[121],"When":[122],"this":[123],"is":[125,139],"state-level":[129],"Bayes":[131],"risk":[132],"criterion,":[133],"27.7%.":[140]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":30},{"year":2014,"cited_by_count":38},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}