{"id":"https://openalex.org/W203263755","doi":"https://doi.org/10.21437/interspeech.2004-178","title":"Optimal acoustic and language model weights for minimizing word verification errors","display_name":"Optimal acoustic and language model weights for minimizing word verification errors","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W203263755","doi":"https://doi.org/10.21437/interspeech.2004-178","mag":"203263755"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-178","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111646360","display_name":"Wai Kit Lo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai Kit Lo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065394791"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1628,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93652918,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"441","last_page":"444"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T12031","display_name":"Speech and dialogue systems","score":0.972000002861023,"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":0.7793364524841309},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5714905858039856},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35801568627357483},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1164848804473877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7793364524841309},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5714905858039856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35801568627357483},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1164848804473877},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-178","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-178","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.148.9805","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.148.9805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.se.cuhk.edu.hk/~wklo/docpub/SoongICSLP2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W55333121","https://openalex.org/W229329885","https://openalex.org/W854561988","https://openalex.org/W2131642018","https://openalex.org/W2134659216","https://openalex.org/W2135936685","https://openalex.org/W2171074980"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Generalized":[0],"word":[1,33,128,173],"posterior":[2],"probability":[3],"(GWPP),":[4],"a":[5,50,65,69,75,110,140,144,171],"confidence":[6,164],"measure":[7],"for":[8,59,163,170],"verifying":[9],"recognized":[10],"words,":[11],"needs":[12],"to":[13,23,40,133],"equalize":[14],"and":[15,18,37,44,74,89,167],"weight":[16],"acoustic":[17,88,118,136],"language":[19,90,124],"model":[20,91,119,125],"likelihood":[21],"contributions":[22],"minimize":[24],"verification":[25,34,47],"errors.":[26],"In":[27],"this":[28],"study,":[29],"we":[30],"investigate":[31],"the":[32,45,61,94,100,105,114,117,134,155],"error":[35,165],"surface":[36],"use":[38],"it":[39],"optimize":[41],"these":[42],"weights":[43],"corresponding":[46],"threshold":[48],"in":[49,126,139],"development":[51],"set.":[52],"We":[53],"test":[54],"three":[55,80],"different":[56],"search":[57,81],"algorithms":[58],"finding":[60],"optimal":[62],"parameters,":[63],"including:":[64],"full":[66],"grid":[67],"search,":[68,73],"gradient-based":[70],"steepest":[71],"descent":[72],"downhill":[76],"simplex":[77],"search.":[78],"The":[79],"methods":[82],"yield":[83],"very":[84],"similar":[85],"solutions.":[86],"Proper":[87],"weights,":[92],"especially":[93],"ratio":[95],"between":[96,104],"them,":[97],"changes":[98],"with":[99],"relative":[101,157],"importance":[102],"(reliability)":[103],"two":[106],"knowledge":[107],"sources.":[108],"For":[109],"narrow":[111,141],"beam":[112],"width,":[113],"role":[115],"of":[116],"is":[120,131,160],"less":[121],"critical":[122],"than":[123],"GWPP-based":[127],"verification,":[129],"which":[130],"due":[132],"noisy":[135],"information":[137],"maintained":[138],"beam.":[142],"Using":[143],"large":[145],"vocabulary":[146],"continuous":[147],"Japanese":[148],"speech":[149],"database":[150],"(Basic":[151],"Travel":[152],"Expression":[153],"Corpus),":[154],"largest":[156],"improvement":[158],"obtained":[159],"33.2":[161],"%":[162,169],"rate":[166],"38.7":[168],"modified":[172],"accuracy.":[174],"1.":[175]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}