{"id":"https://openalex.org/W1679128","doi":"https://doi.org/10.21437/interspeech.2004-363","title":"Mis-recognized utterance detection using hierarchical language model","display_name":"Mis-recognized utterance detection using hierarchical language model","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W1679128","doi":"https://doi.org/10.21437/interspeech.2004-363","mag":"1679128"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-363","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-363","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/A5109832868","display_name":"Hirofumi Yamamoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hirofumi Yamamoto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051791256","display_name":"Genichiro Kikui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Genichiro Kikui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045034259","display_name":"Yoshinori Sagisaka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinori Sagisaka","raw_affiliation_strings":["Advanced Telecommunications Research Institute International"],"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109832868"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00026555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1025","last_page":"1028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908000230789185,"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":0.9735999703407288,"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/utterance","display_name":"Utterance","score":0.8723020553588867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852450609207153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7148743867874146},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7044409513473511},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5585487484931946},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.54639732837677},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5178371071815491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5126785039901733},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4968266785144806},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43397796154022217},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37264853715896606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10450512170791626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09531077742576599}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8723020553588867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852450609207153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7148743867874146},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7044409513473511},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5585487484931946},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.54639732837677},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5178371071815491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5126785039901733},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4968266785144806},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43397796154022217},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37264853715896606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10450512170791626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09531077742576599},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-363","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-363","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W132009480","https://openalex.org/W216110655","https://openalex.org/W229329885","https://openalex.org/W252391729","https://openalex.org/W854561988","https://openalex.org/W1971081490","https://openalex.org/W2068970468","https://openalex.org/W2131642018","https://openalex.org/W2134473597","https://openalex.org/W2155852061","https://openalex.org/W2165112885"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W1494910745"],"abstract_inverted_index":{"In":[0,20],"this":[1,93],"paper,":[2],"a":[3,21,54,96,127,142],"mis-recognized":[4,106],"utterance":[5,85,107],"detection":[6,113,129,161],"and":[7,39,50,70,105,162],"modification":[8,163],"scheme":[9],"is":[10,26,82,121,139],"proposed":[11,159],"to":[12,58,141],"recover":[13],"speech":[14,18,22,102],"recognition":[15,23,103],"errors":[16],"in":[17],"translation.":[19],"stage,":[24],"mis-recognition":[25],"frequently":[27],"observed.":[28],"The":[29,134],"most":[30],"of":[31,36,79,92,126,136,157],"mis-recognitions":[32],"result":[33],"from":[34],"mis-match":[35,49],"acoustic":[37,47,74],"models":[38],"out-of-vocabulary":[40],"(OOV)":[41],"words.":[42],"To":[43,88],"cope":[44],"with":[45,69,117],"both":[46,67],"model":[48,57,64],"OOVs,":[51],"we":[52,99],"adopt":[53],"hierarchical":[55,62],"language":[56,63],"identify":[59],"them.":[60],"A":[61],"can":[65],"generate":[66],"hypotheses":[68,81],"without":[71,150],"OOVs":[72],"(or":[73],"mis-matched":[75],"words).":[76],"Likelihood":[77],"difference":[78],"these":[80],"used":[83],"as":[84,95],"confidence":[86],"measure.":[87],"confirm":[89],"the":[90,148,155,158],"possibility":[91,156],"scheme,":[94],"first":[97],"experiment,":[98],"have":[100],"conducted":[101],"experiments":[104],"detection.":[108],"Experiment":[109],"results":[110,153],"showed":[111],"99%":[112],"rate":[114,120,135],"for":[115,147],"utterances":[116,149],"OOVs.":[118,151],"This":[119],"considerably":[122],"higher":[123],"than":[124],"94%":[125],"conventional":[128,143],"method":[130,144],"using":[131],"a-posteriori":[132],"probability.":[133],"80%,":[137],"which":[138],"comparable":[140],"were":[145],"obtained":[146],"These":[152],"support":[154],"error":[160],"scheme.":[164]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}