{"id":"https://openalex.org/W4408352239","doi":"https://doi.org/10.1109/icassp49660.2025.10890024","title":"Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores","display_name":"Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352239","doi":"https://doi.org/10.1109/icassp49660.2025.10890024"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101880813","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0000-0002-0043-3645"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101473591","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-0023-3715"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669565","display_name":"Tianhao Zhang","orcid":"https://orcid.org/0000-0002-5939-3932"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian-Hao Zhang","raw_affiliation_strings":["University of Science and Technology Beijing,Beijing,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,Beijing,China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035524175","display_name":"Haoqin Sun","orcid":"https://orcid.org/0000-0002-8554-8969"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqin Sun","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101483730","display_name":"Xuechen Wang","orcid":"https://orcid.org/0000-0002-3584-7821"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuechen Wang","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai University,TMCC, College of Computer Science,Tianjin,China"],"affiliations":[{"raw_affiliation_string":"Nankai University,TMCC, College of Computer Science,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101880813"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":6.5456,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95778312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"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":0.9929999709129333,"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":0.9871000051498413,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9840999841690063,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/code-switching","display_name":"Code-switching","score":0.7089947462081909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6982321739196777},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5720803737640381},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5023767948150635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4352269768714905},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42500150203704834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3411819338798523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33178457617759705},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18539321422576904},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12217780947685242},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07064154744148254}],"concepts":[{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7089947462081909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6982321739196777},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5720803737640381},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5023767948150635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4352269768714905},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42500150203704834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3411819338798523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33178457617759705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18539321422576904},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12217780947685242},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07064154744148254},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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:10.1109/icassp49660.2025.10890024","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890024","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":36,"referenced_works":["https://openalex.org/W2091715339","https://openalex.org/W2127141656","https://openalex.org/W2786835190","https://openalex.org/W2891616026","https://openalex.org/W2979826702","https://openalex.org/W2998702515","https://openalex.org/W3096122506","https://openalex.org/W3097777922","https://openalex.org/W3178647810","https://openalex.org/W3197478142","https://openalex.org/W3198429080","https://openalex.org/W3203407300","https://openalex.org/W4297841565","https://openalex.org/W4372269995","https://openalex.org/W4372347360","https://openalex.org/W4375869316","https://openalex.org/W4385822790","https://openalex.org/W4385822813","https://openalex.org/W4385822890","https://openalex.org/W4385823213","https://openalex.org/W4385823334","https://openalex.org/W4385895585","https://openalex.org/W4388017359","https://openalex.org/W4391021741","https://openalex.org/W4392903240","https://openalex.org/W4392910591","https://openalex.org/W4402111964","https://openalex.org/W4402112225","https://openalex.org/W4406461303","https://openalex.org/W4408353073","https://openalex.org/W6770813465","https://openalex.org/W6780815891","https://openalex.org/W6783813245","https://openalex.org/W6810476118","https://openalex.org/W6847363464","https://openalex.org/W6873278751"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W3158134258","https://openalex.org/W2773965352","https://openalex.org/W3138119129","https://openalex.org/W2940588741"],"abstract_inverted_index":{"The":[0],"kNN-CTC":[1,33],"model":[2,34],"has":[3],"proven":[4],"to":[5,18,72,100],"be":[6],"effective":[7],"for":[8,29,82],"monolingual":[9,64],"automatic":[10],"speech":[11],"recognition":[12],"(ASR).":[13],"However,":[14],"its":[15],"direct":[16],"application":[17],"multilingual":[19],"scenarios":[20],"like":[21],"code-switching,":[22],"presents":[23],"challenges.":[24],"Although":[25],"there":[26],"is":[27],"potential":[28],"performance":[30,123],"improvement,":[31],"a":[32,36,54,67],"utilizing":[35],"single":[37],"bilingual":[38],"datastore":[39,69,81,118],"can":[40],"inadvertently":[41],"introduce":[42],"undesirable":[43],"noise":[44,74],"from":[45],"the":[46,79,87,93,112,122],"alternative":[47],"language.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"novel":[55],"kNN-CTC-based":[56],"code-switching":[57],"ASR":[58,94],"(CS-ASR)":[59],"framework":[60,99],"that":[61],"employs":[62],"dual":[63],"datastores":[65],"and":[66],"gated":[68,117],"selection":[70],"mechanism":[71,119],"reduce":[73],"interference.":[75],"Our":[76],"method":[77],"selects":[78],"appropriate":[80],"decoding":[83],"each":[84],"frame,":[85],"ensuring":[86],"injection":[88],"of":[89,115,124],"language-specific":[90],"information":[91],"into":[92],"process.":[95],"We":[96],"apply":[97],"this":[98],"cutting-edge":[101],"CTC-based":[102],"models,":[103],"developing":[104],"an":[105],"advanced":[106],"CS-ASR":[107],"system.":[108],"Extensive":[109],"experiments":[110],"demonstrate":[111],"remarkable":[113],"effectiveness":[114],"our":[116],"in":[120],"enhancing":[121],"zero-shot":[125],"Chinese-English":[126],"CS-ASR.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}