{"id":"https://openalex.org/W3198004110","doi":"https://doi.org/10.21437/interspeech.2021-1566","title":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","display_name":"Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198004110","doi":"https://doi.org/10.21437/interspeech.2021-1566","mag":"3198004110"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1566","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5103098852","display_name":"Duc Le","orcid":"https://orcid.org/0000-0001-9490-2563"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Duc Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112701957","display_name":"Mahaveer Jain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahaveer Jain","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048538280","display_name":"Gil Keren","orcid":"https://orcid.org/0000-0002-5153-3494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gil Keren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051075420","display_name":"Julian Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julian Chan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047358828","display_name":"Yuan Shangguan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Shangguan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066166549","display_name":"Ozlem Kalinli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051165898","display_name":"Yatharth Saraf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yatharth Saraf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5103098852"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9957,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.97469425,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1772","last_page":"1776"},"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":0.9940999746322632,"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":0.9922000169754028,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6478754281997681},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6371814012527466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5651724338531494},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.5146639943122864},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4498542547225952},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.43810591101646423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3257511258125305},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15741074085235596},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1397538185119629},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1350441575050354},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12001484632492065}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6478754281997681},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6371814012527466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5651724338531494},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.5146639943122864},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4498542547225952},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.43810591101646423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3257511258125305},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15741074085235596},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1397538185119629},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1350441575050354},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12001484632492065},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1566","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1566","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2407080277","https://openalex.org/W2750499125","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2936774411","https://openalex.org/W2939111082","https://openalex.org/W2962760690","https://openalex.org/W2963240019","https://openalex.org/W2963250244","https://openalex.org/W2963362078","https://openalex.org/W2963979492","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3008037978","https://openalex.org/W3008525923","https://openalex.org/W3015486229","https://openalex.org/W3016234571","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3140235797","https://openalex.org/W3146505093","https://openalex.org/W3149509723","https://openalex.org/W3152221657","https://openalex.org/W3162639446","https://openalex.org/W3162665866","https://openalex.org/W4287605195"],"related_works":["https://openalex.org/W2376605347","https://openalex.org/W3107474891","https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W3128571556","https://openalex.org/W4304891817"],"abstract_inverted_index":{"How":[0],"to":[1,17,32,38,87],"leverage":[2],"dynamic":[3],"contextual":[4,81],"information":[5],"in":[6,71],"end-toend":[7],"speech":[8],"recognition":[9],"has":[10],"remained":[11],"an":[12],"active":[13],"research":[14],"area.Previous":[15],"solutions":[16],"this":[18],"problem":[19],"were":[20],"either":[21],"designed":[22],"for":[23,115],"specialized":[24],"use":[25],"cases":[26],"that":[27,56],"did":[28,35],"not":[29,36],"generalize":[30],"well":[31],"open-domain":[33,94],"scenarios,":[34],"scale":[37],"large":[39],"biasing":[40,82],"lists,":[41],"or":[42],"underperformed":[43],"on":[44,92],"rare":[45,105],"long-tail":[46,106],"words.We":[47],"address":[48],"these":[49],"limitations":[50],"by":[51],"proposing":[52],"a":[53,88],"novel":[54],"solution":[55],"combines":[57],"shallow":[58],"fusion,":[59],"trie-based":[60],"deep":[61],"biasing,":[62],"and":[63,84,95,112],"neural":[64],"network":[65],"language":[66],"model":[67,119],"contextualization.These":[68],"techniques":[69],"result":[70],"significant":[72],"19.5%":[73],"relative":[74],"Word":[75],"Error":[76],"Rate":[77],"improvement":[78],"over":[79],"existing":[80],"approaches":[83],"5.4%-9.3%improvement":[85],"compared":[86],"strong":[89],"hybrid":[90],"baseline":[91],"both":[93],"constrained":[96],"contextualization":[97],"tasks,":[98],"where":[99],"the":[100],"targets":[101],"consist":[102],"of":[103],"mostly":[104],"words.Our":[107],"final":[108],"system":[109],"remains":[110],"lightweight":[111],"modular,":[113],"allowing":[114],"quick":[116],"modification":[117],"without":[118],"re-training.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}