{"id":"https://openalex.org/W4406461293","doi":"https://doi.org/10.1109/slt61566.2024.10832154","title":"CTC-Assisted LLM-Based Contextual ASR","display_name":"CTC-Assisted LLM-Based Contextual ASR","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461293","doi":"https://doi.org/10.1109/slt61566.2024.10832154"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5111310847","display_name":"Guanrou Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guanrou Yang","raw_affiliation_strings":["AI Institute X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"AI Institute X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Ma","raw_affiliation_strings":["AI Institute X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"AI Institute X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109593343","display_name":"Zhifu Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifu Gao","raw_affiliation_strings":["Alibaba Group,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100329117","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-5801-2571"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["AI Institute X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China"],"affiliations":[{"raw_affiliation_string":"AI Institute X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111310847"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.6528,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91564665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"131"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9987000226974487,"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":0.988099992275238,"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":0.6742476224899292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6742476224899292}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2395440424","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2903250132","https://openalex.org/W2972625221","https://openalex.org/W3097239815","https://openalex.org/W3097794466","https://openalex.org/W3160413945","https://openalex.org/W3198004110","https://openalex.org/W3209984917","https://openalex.org/W3211278025","https://openalex.org/W4283832239","https://openalex.org/W4385822246","https://openalex.org/W4385822295","https://openalex.org/W4391021666","https://openalex.org/W4391835492","https://openalex.org/W4392903019","https://openalex.org/W4392903078","https://openalex.org/W4392903329","https://openalex.org/W4392909899","https://openalex.org/W4402112425","https://openalex.org/W6861626678"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Contextual":[0,70],"ASR":[1,34,58,71,133,157],"or":[2],"hotword":[3],"customization":[4],"holds":[5],"substantial":[6],"practical":[7],"value.":[8],"Despite":[9],"the":[10,62,113,130,144,147],"impressive":[11],"performance":[12,45],"of":[13,100,146],"current":[14],"end-to-end":[15],"(E2E)":[16],"automatic":[17],"speech":[18],"recognition":[19],"(ASR)":[20],"systems,":[21],"they":[22],"often":[23],"face":[24],"challenges":[25],"in":[26,44],"accurately":[27],"recognizing":[28,121],"rare":[29,122],"words.":[30,52],"Typical":[31],"E2E":[32],"contextual":[33,156],"models":[35,59],"commonly":[36],"feature":[37],"complex":[38],"architectures":[39],"and":[40,46,89,106,116,135,151],"decoding":[41,82],"mechanisms,":[42],"limited":[43],"susceptible":[47],"to":[48,84,129],"interference":[49],"from":[50],"distractor":[51],"With":[53],"large":[54,148],"language":[55,149],"model":[56,72,97,150,158],"(LLM)-based":[57],"emerging":[60],"as":[61],"new":[63],"mainstream,":[64],"we":[65],"propose":[66],"a":[67],"CTC-Assisted":[68],"LLM-Based":[69],"with":[73,143,162],"an":[74],"efficient":[75],"filtering":[76,153],"algorithm.":[77],"By":[78],"using":[79],"coarse":[80],"CTC":[81],"results":[83],"filter":[85],"potential":[86],"relevant":[87],"hotwords":[88],"incorporating":[90],"them":[91],"into":[92],"LLM":[93],"prompt":[94],"input,":[95],"our":[96,155],"attains":[98],"WER/B-WER":[99],"$1.27":[101],"\\%":[102,108],"/":[103,109],"3.67":[104],"\\%$":[105,111],"$2.72":[107],"8.02":[110],"on":[112,120],"Librispeech":[114],"test-clean":[115],"test-other":[117],"sets":[118],"targeting":[119],"long-tail":[123],"words,":[124],"demonstrating":[125],"significant":[126],"improvements":[127],"compared":[128],"baseline":[131],"LLM-based":[132],"model,":[134],"substantially":[136],"surpassing":[137],"other":[138],"related":[139],"work.":[140],"More":[141],"remarkably,":[142],"help":[145],"proposed":[152],"algorithm,":[154],"still":[159],"performs":[160],"well":[161],"2000":[163],"biasing":[164],"words.<sup":[165],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[166],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}