{"id":"https://openalex.org/W3160335057","doi":"https://doi.org/10.1109/icassp39728.2021.9413756","title":"Improving Entity Recall in Automatic Speech Recognition with Neural Embeddings","display_name":"Improving Entity Recall in Automatic Speech Recognition with Neural Embeddings","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160335057","doi":"https://doi.org/10.1109/icassp39728.2021.9413756","mag":"3160335057"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5081862797","display_name":"Christopher Li","orcid":"https://orcid.org/0000-0003-3763-3891"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher Li","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066360541","display_name":"Pat Rondon","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pat Rondon","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021056932","display_name":"Diamantino Caseiro","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Diamantino Caseiro","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069649488","display_name":"Leonid Velikovich","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Velikovich","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077786635","display_name":"Xavier Velez","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xavier Velez","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081890177","display_name":"Petar Aleksic","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Petar Aleksic","raw_affiliation_strings":["Google, Inc"],"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5081862797"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61331219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7353","last_page":"7357"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9977999925613403,"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":0.7440761923789978},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.7187617421150208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7069088220596313},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.507082462310791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5017733573913574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4148636758327484},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11483532190322876},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1114484965801239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440761923789978},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.7187617421150208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7069088220596313},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.507082462310791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5017733573913574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4148636758327484},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11483532190322876},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1114484965801239}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2121879602","https://openalex.org/W2271840356","https://openalex.org/W2296545762","https://openalex.org/W2327501763","https://openalex.org/W2403440562","https://openalex.org/W2407023693","https://openalex.org/W2523246573","https://openalex.org/W2578392894","https://openalex.org/W2586604101","https://openalex.org/W2745671704","https://openalex.org/W2747467128","https://openalex.org/W2888779557","https://openalex.org/W2901894078","https://openalex.org/W2939111082","https://openalex.org/W2963609956","https://openalex.org/W2963977978","https://openalex.org/W2964221236","https://openalex.org/W2972613398","https://openalex.org/W2973056893","https://openalex.org/W2987249037","https://openalex.org/W2995154514","https://openalex.org/W3015194534","https://openalex.org/W3024786184","https://openalex.org/W3034696692","https://openalex.org/W3041679645","https://openalex.org/W3097239815","https://openalex.org/W4288087322","https://openalex.org/W6638749077","https://openalex.org/W6694517276","https://openalex.org/W6713395095","https://openalex.org/W6714171909","https://openalex.org/W6727249380","https://openalex.org/W6756140488","https://openalex.org/W6768099513","https://openalex.org/W6770813465","https://openalex.org/W6777399232"],"related_works":["https://openalex.org/W2118758177","https://openalex.org/W4330338194","https://openalex.org/W2153520307","https://openalex.org/W2151459719","https://openalex.org/W623261610","https://openalex.org/W2316630966","https://openalex.org/W4401374939","https://openalex.org/W1976696937","https://openalex.org/W2059453987","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2],"(ASR)":[3],"systems":[4],"often":[5],"have":[6,76],"difficulty":[7],"recognizing":[8],"long-tail":[9],"entities":[10,96],"such":[11],"as":[12],"contact":[13],"names":[14],"and":[15,44,91,97,133,143,165],"local":[16],"restaurant":[17],"names,":[18],"which":[19,39],"usually":[20],"do":[21],"not":[22],"occur,":[23],"or":[24],"occur":[25],"infrequently,":[26],"in":[27,130,160,168],"the":[28,70,81,84,114,126,131,134,137,140,144,147],"system\u2019s":[29],"training":[30],"data.":[31],"In":[32],"this":[33,151],"work,":[34],"we":[35,101,155],"present":[36],"a":[37,49,64,87,92,123,157],"method":[38],"uses":[40],"learned":[41],"text":[42,59,85,142],"embeddings":[43,54,60,71],"nearest":[45,105],"neighbor":[46,106],"retrieval":[47,107],"within":[48,113],"large":[50],"database":[51,94],"of":[52,72,83,86,125,139,146],"entity":[53,89],"to":[55,109],"correct":[56],"misrecognitions.":[57],"Our":[58],"are":[61,119],"produced":[62],"by":[63],"neural":[65],"network":[66],"trained":[67],"so":[68],"that":[69],"acoustically":[73],"confusable":[74],"phrases":[75],"low":[77],"cosine":[78],"distances.":[79],"Given":[80],"embedding":[82,138,145],"potential":[88],"misrecognition":[90],"precomputed":[93],"containing":[95],"their":[98],"corresponding":[99],"embeddings,":[100],"use":[102],"fast,":[103],"scalable":[104],"algorithms":[108],"find":[110],"candidate":[111,148],"corrections":[112],"database.":[115],"The":[116],"inserted":[117],"candidates":[118],"then":[120],"scored":[121],"using":[122],"function":[124],"original":[127,141],"text\u2019s":[128],"cost":[129],"lattice":[132,152],"distance":[135],"between":[136],"correction.":[149],"Using":[150],"augmentation":[153],"techique,":[154],"demonstrate":[156],"46%":[158,166],"reduction":[159,167],"word":[161,170],"error":[162,171],"rate":[163,172],"(WER)":[164],"oracle":[169],"(OWER)":[173],"on":[174],"an":[175],"evaluation":[176],"set":[177],"with":[178],"popular":[179],"film":[180],"queries.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}