{"id":"https://openalex.org/W2135939555","doi":"https://doi.org/10.1109/icassp.2004.1326111","title":"Optimizing acoustic models for commercial speech recognition using foreground scores and data weighting","display_name":"Optimizing acoustic models for commercial speech recognition using foreground scores and data weighting","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2135939555","doi":"https://doi.org/10.1109/icassp.2004.1326111","mag":"2135939555"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5028907264","display_name":"Daniel Boies","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["AT","US"],"is_corresponding":true,"raw_author_name":"D. Boies","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA","Nuance Commun., Menlo Park, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Commun., Menlo Park, CA, USA#TAB#","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001487094","display_name":"Brian Strope","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"B. Strope","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA","Nuance Commun., Menlo Park, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Commun., Menlo Park, CA, USA#TAB#","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108513736","display_name":"M. Weintraub","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"M. Weintraub","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA","Nuance Commun., Menlo Park, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Commun., Menlo Park, CA, USA#TAB#","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080017989","display_name":"Su-Lin Wu","orcid":"https://orcid.org/0009-0009-0425-1177"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Su-Lin Wu","raw_affiliation_strings":["Nuance Communications, Menlo Park, CA, USA","Nuance Commun., Menlo Park, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Nuance Communications, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210125787"]},{"raw_affiliation_string":"Nuance Commun., Menlo Park, CA, USA#TAB#","institution_ids":["https://openalex.org/I1292318990"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028907264"],"corresponding_institution_ids":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20144261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.8253545165061951},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302596569061279},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6336826086044312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5996836423873901},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5084763765335083},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49477285146713257},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4944896697998047},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48878785967826843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4620949327945709},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4466271698474884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4454513192176819},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4373442530632019},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4326850473880768},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34675663709640503},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08914166688919067},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.08034276962280273}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8253545165061951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302596569061279},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6336826086044312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5996836423873901},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5084763765335083},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49477285146713257},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4944896697998047},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48878785967826843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4620949327945709},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4466271698474884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4454513192176819},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4373442530632019},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4326850473880768},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34675663709640503},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08914166688919067},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.08034276962280273},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326111","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326111","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.9491","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.9491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-gth.die.upm.es/research/documentation/referencias/Boies_Optimizing.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W103129759","https://openalex.org/W1486915487","https://openalex.org/W1877570817","https://openalex.org/W1988790447","https://openalex.org/W2033565080","https://openalex.org/W2067771110","https://openalex.org/W2093677674","https://openalex.org/W2098773974","https://openalex.org/W2100169672","https://openalex.org/W2157749010","https://openalex.org/W3146702093","https://openalex.org/W3146777338","https://openalex.org/W6629170297"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W2131711534","https://openalex.org/W3143423642","https://openalex.org/W2341426843"],"abstract_inverted_index":{"This":[0,45],"paper":[1],"describes":[2],"a":[3,71],"data-driven":[4],"technique":[5],"for":[6,11,41,56],"optimizing":[7],"the":[8,42,51,77,83],"acoustic":[9,43,84],"models":[10],"speech":[12],"recognition":[13,28],"systems":[14],"that":[15],"target":[16],"commercial":[17],"applications":[18],"over":[19],"telephones.":[20],"Frame-averaged":[21],"foreground":[22],"log-likelihoods":[23],"(foreground":[24],"scores)":[25],"correlate":[26],"to":[27,37,64,81],"errors.":[29],"These":[30],"scores":[31],"are":[32],"used":[33,80],"together":[34],"with":[35],"gender":[36],"optimize":[38],"data":[39,79],"weighting":[40],"model.":[44,85],"process":[46],"is":[47],"interpreted":[48],"as":[49],"increasing":[50],"priors":[52],"and":[53],"associated":[54],"parameters":[55],"poorly":[57],"modeled":[58],"data.":[59],"The":[60],"score-based":[61],"optimization":[62],"leads":[63],"about":[65],"7%":[66],"fewer":[67],"semantic":[68],"errors":[69],"on":[70],"live":[72],"evaluation":[73],"set":[74],"collected":[75],"after":[76],"last":[78],"estimate":[82]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}