{"id":"https://openalex.org/W2914603327","doi":"https://doi.org/10.1109/slt.2018.8639563","title":"Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR","display_name":"Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914603327","doi":"https://doi.org/10.1109/slt.2018.8639563","mag":"2914603327"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"212","last_page":"218"},"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":0.9988999962806702,"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.8375126719474792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6973167061805725},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6448696255683899},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.606685996055603},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5946983695030212},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47153955698013306},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.47044816613197327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38582202792167664},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07034969329833984},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06909525394439697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8375126719474792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6973167061805725},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6448696255683899},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.606685996055603},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5946983695030212},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47153955698013306},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.47044816613197327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38582202792167664},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07034969329833984},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06909525394439697},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1815076433","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2166637769","https://openalex.org/W2183341477","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2549416390","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2749738822","https://openalex.org/W2750499125","https://openalex.org/W2752168051","https://openalex.org/W2890197052","https://openalex.org/W2899771611","https://openalex.org/W2962813140","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962964385","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963266252","https://openalex.org/W2963303028","https://openalex.org/W2963347649","https://openalex.org/W2963483399","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2963970535","https://openalex.org/W2963980299","https://openalex.org/W2964121744","https://openalex.org/W3034729383","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6638545294","https://openalex.org/W6687566353","https://openalex.org/W6729239390","https://openalex.org/W6736086397","https://openalex.org/W6741807409","https://openalex.org/W6743063357","https://openalex.org/W6743440867","https://openalex.org/W6743489131","https://openalex.org/W6746299031","https://openalex.org/W6746574493","https://openalex.org/W6756040250","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2349784553","https://openalex.org/W2017509870","https://openalex.org/W2542937328","https://openalex.org/W3022596247","https://openalex.org/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Acoustic-to-word":[0],"(A2W)":[1],"end-to-end":[2],"automatic":[3],"speech":[4],"recognition":[5],"(ASR)":[6],"systems":[7],"have":[8,107,131],"attracted":[9],"attention":[10],"because":[11],"of":[12,62,134,144,170,174],"an":[13,32],"extremely":[14],"simplified":[15],"architecture":[16],"and":[17,72,106,148,158,177],"fast":[18],"decoding.":[19],"To":[20],"alleviate":[21],"data":[22,179],"sparseness":[23],"issues":[24],"due":[25],"to":[26,45,77,111,120],"infrequent":[27],"words,":[28,147],"the":[29,39,54,85,132,142,149,168,171,178,189],"combination":[30],"with":[31,69,104,194],"acoustic-to-character":[33],"(A2C)":[34],"model":[35,41,117],"is":[36,118],"investigated.":[37],"Moreover,":[38,184],"A2C":[40,116],"can":[42,187],"be":[43],"used":[44,119],"recover-of-vocabulary":[46],"(OOV)":[47],"words":[48,81,83],"that":[49,128],"are":[50,101],"not":[51,135],"covered":[52],"by":[53,94],"A2W":[55,65,175],"model,":[56],"but":[57,139],"this":[58,88,92],"requires":[59],"accurate":[60],"detection":[61],"OOV":[63,80,113,123,146],"words.":[64,114,124],"models":[66,98,176],"learn":[67],"contexts":[68],"both":[70],"acoustic":[71],"transcripts;":[73],"therefore":[74],"they":[75],"tend":[76],"falsely":[78],"recognize":[79],"as":[82],"in":[84,155],"vocabulary.":[86],"In":[87],"paper,":[89],"we":[90],"tackle":[91],"problem":[93],"using":[95],"external":[96,129],"language":[97],"(LM),":[99],"which":[100],"trained":[102],"only":[103,136],"transcriptions":[105],"better":[108],"linguistic":[109],"information":[110],"detect":[112],"The":[115],"resolve":[121],"these":[122],"Experimental":[125],"evaluations":[126],"show":[127],"LMs":[130],"effects":[133],"reducing":[137],"errors":[138],"also":[140,166],"increasing":[141],"number":[143],"detected":[145],"proposed":[150],"method":[151],"significantly":[152],"improves":[153],"performances":[154],"English":[156],"conversational":[157],"Japanese":[159],"lecture":[160],"corpora,":[161],"especially":[162],"for-of-domain":[163],"scenario.":[164],"We":[165],"investigate":[167],"impact":[169],"vocabulary":[172,190],"size":[173,180,191],"for":[181],"training":[182],"LMs.":[183],"our":[185],"approach":[186],"reduce":[188],"several":[192],"times":[193],"marginal":[195],"performance":[196],"degradation.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}