{"id":"https://openalex.org/W2898599211","doi":"https://doi.org/10.1109/icassp.2019.8682738","title":"Contextual Speech Recognition with Difficult Negative Training Examples","display_name":"Contextual Speech Recognition with Difficult Negative Training Examples","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2898599211","doi":"https://doi.org/10.1109/icassp.2019.8682738","mag":"2898599211"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5107243336","display_name":"Uri Alon","orcid":"https://orcid.org/0000-0001-5796-9988"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Uri Alon","raw_affiliation_strings":["Technion, Israel"],"affiliations":[{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051090720","display_name":"Golan Pundak","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":"Golan Pundak","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107243336"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":2.7662,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9241301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6440","last_page":"6444"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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":0.8590923547744751},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8379607200622559},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.679254949092865},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6348188519477844},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6333094835281372},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.617002546787262},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.594083309173584},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5649263262748718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5518656969070435},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5385464429855347},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.481625497341156},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.44134756922721863},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14750754833221436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590923547744751},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8379607200622559},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.679254949092865},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6348188519477844},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6333094835281372},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.617002546787262},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.594083309173584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5649263262748718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5518656969070435},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5385464429855347},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.481625497341156},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.44134756922721863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14750754833221436},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682738","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682738","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1604697534","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1940872118","https://openalex.org/W2163605009","https://openalex.org/W2271840356","https://openalex.org/W2296237247","https://openalex.org/W2327501763","https://openalex.org/W2545177271","https://openalex.org/W2617258110","https://openalex.org/W2748584437","https://openalex.org/W2769810959","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963572611","https://openalex.org/W2963747784","https://openalex.org/W2963782041","https://openalex.org/W2963920996","https://openalex.org/W4294619240","https://openalex.org/W6629052376","https://openalex.org/W6636649193","https://openalex.org/W6637852806","https://openalex.org/W6640362995","https://openalex.org/W6684191040","https://openalex.org/W6697235383"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W2162582511","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Improving":[0],"the":[1,10,59,71,96],"representation":[2],"of":[3,12,54],"contextual":[4,86],"information":[5],"is":[6,42],"key":[7],"to":[8,43,74,83,92,108],"unlocking":[9],"potential":[11],"end-to-end":[13,85],"(E2E)":[14],"automatic":[15],"speech":[16],"recognition":[17],"(ASR).":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"present":[23],"a":[24],"novel":[25],"and":[26,56,62,94],"simple":[27],"approach":[28,82],"for":[29],"training":[30],"an":[31,84],"ASR":[32,87],"context":[33,98],"mechanism":[34],"with":[35],"difficult":[36],"negative":[37,68],"examples.":[38],"The":[39],"main":[40],"idea":[41],"focus":[44],"on":[45],"proper":[46],"nouns":[47],"(e.g.,":[48],"unique":[49],"entities":[50],"such":[51],"as":[52,67],"names":[53],"people":[55],"places)":[57],"in":[58,112],"reference":[60],"transcript":[61],"use":[63],"phonetically":[64],"similar":[65],"phrases":[66],"examples,":[69],"encouraging":[70],"neural":[72],"model":[73,88],"learn":[75],"more":[76],"discriminative":[77],"representations.":[78],"We":[79,100],"apply":[80],"our":[81,103],"that":[89,102],"jointly":[90],"learns":[91],"transcribe":[93],"select":[95],"correct":[97],"items.":[99],"show":[101],"proposed":[104],"method":[105],"gives":[106],"up":[107],"53.1%":[109],"relative":[110],"improvement":[111],"word":[113],"error":[114],"rate":[115],"(WER)":[116],"across":[117],"several":[118],"benchmarks.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}