{"id":"https://openalex.org/W4372259815","doi":"https://doi.org/10.1109/icassp49357.2023.10094689","title":"Named Entity Detection and Injection for Direct Speech Translation","display_name":"Named Entity Detection and Injection for Direct Speech Translation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259815","doi":"https://doi.org/10.1109/icassp49357.2023.10094689"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094689","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5054564363","display_name":"Marco Gaido","orcid":"https://orcid.org/0000-0003-4217-1396"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Gaido","raw_affiliation_strings":["Meta AI,USA","Fondazione Bruno Kessler, Italy","Meta AI, USA","University of Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]},{"raw_affiliation_string":"University of Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052049405","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0003-2340-1109"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Tang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110668","display_name":"Ilia Kulikov","orcid":"https://orcid.org/0000-0001-5989-9733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilia Kulikov","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110198056","display_name":"Rongqing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongqing Huang","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103000746","display_name":"Hongyu Gong","orcid":"https://orcid.org/0000-0002-7071-0070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyu Gong","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39166279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","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/T12031","display_name":"Speech and dialogue systems","score":0.9951000213623047,"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":0.8174551725387573},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.733268678188324},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6624881625175476},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6513808369636536},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5972955226898193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5648203492164612},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5348915457725525},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.48825979232788086},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4849989116191864},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.46476778388023376},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4404025077819824},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1313251554965973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174551725387573},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.733268678188324},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6624881625175476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6513808369636536},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5972955226898193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5648203492164612},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5348915457725525},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.48825979232788086},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4849989116191864},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.46476778388023376},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4404025077819824},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1313251554965973},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094689","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10094689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W2250821182","https://openalex.org/W2886319145","https://openalex.org/W2963506925","https://openalex.org/W2963532001","https://openalex.org/W2964029788","https://openalex.org/W2975381464","https://openalex.org/W2978264350","https://openalex.org/W2995181338","https://openalex.org/W3015698636","https://openalex.org/W3032322556","https://openalex.org/W3092085609","https://openalex.org/W3094903517","https://openalex.org/W3097239815","https://openalex.org/W3162042236","https://openalex.org/W3174446152","https://openalex.org/W3176711365","https://openalex.org/W3199713193","https://openalex.org/W4205476602","https://openalex.org/W4221152019","https://openalex.org/W4223622550","https://openalex.org/W4285273653","https://openalex.org/W4287890956","https://openalex.org/W6600880057","https://openalex.org/W6691538871","https://openalex.org/W6768080748","https://openalex.org/W6768855772","https://openalex.org/W6778801828","https://openalex.org/W6795271814"],"related_works":["https://openalex.org/W2161008081","https://openalex.org/W2100947578","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W1974418053","https://openalex.org/W2021532426","https://openalex.org/W1998701884","https://openalex.org/W2898767136"],"abstract_inverted_index":{"In":[0,59],"a":[1,75,120],"sentence,":[2],"certain":[3],"words":[4],"are":[5,15],"critical":[6],"for":[7,18,45],"its":[8],"semantic.":[9],"Among":[10],"them,":[11],"named":[12],"entities":[13],"(NEs)":[14],"notoriously":[16],"challenging":[17,54],"neural":[19],"models.":[20],"Despite":[21],"their":[22,24],"importance,":[23],"accurate":[25],"handling":[26],"has":[27,38],"been":[28],"neglected":[29],"in":[30,57,74,94,116,123],"speech-to-text":[31],"(S2T)":[32],"translation":[33,118],"research,":[34],"and":[35,47],"recent":[36],"work":[37],"shown":[39],"that":[40,86,105],"S2T":[41,80,99],"models":[42],"perform":[43],"poorly":[44],"locations":[46],"notably":[48],"person":[49,124],"names,":[50],"whose":[51],"spelling":[52],"is":[53,110],"unless":[55],"known":[56,70],"advance.":[58],"this":[60],"work,":[61],"we":[62,87,103],"explore":[63],"how":[64],"to":[65,71,78,112],"leverage":[66],"dictionaries":[67],"of":[68],"NEs":[69,91],"likely":[72,92],"appear":[73],"given":[76],"context":[77],"improve":[79,113],"model":[81],"outputs.":[82,101],"Our":[83],"experiments":[84],"show":[85],"can":[88],"reliably":[89],"detect":[90],"present":[93],"an":[95],"utterance":[96],"starting":[97],"from":[98],"encoder":[100],"Indeed,":[102],"demonstrate":[104],"the":[106,117],"current":[107],"detection":[108],"quality":[109],"sufficient":[111],"NE":[114],"accuracy":[115],"with":[119],"31%":[121],"reduction":[122],"name":[125],"errors.":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}