{"id":"https://openalex.org/W4406462011","doi":"https://doi.org/10.1109/slt61566.2024.10832173","title":"Semi-Supervised Learning For Code-Switching ASR With Large Language Model Filter","display_name":"Semi-Supervised Learning For Code-Switching ASR With Large Language Model Filter","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406462011","doi":"https://doi.org/10.1109/slt61566.2024.10832173"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832173","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":"conference-paper","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/A5102383536","display_name":"Yu Xi","orcid":"https://orcid.org/0009-0002-8918-3829"},"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":"Yu Xi","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100723777","display_name":"Wen Ding","orcid":"https://orcid.org/0009-0005-7628-4614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen Ding","raw_affiliation_strings":["NVIDIA Corporation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Shanghai,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"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":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047209626","display_name":"Junjie Lai","orcid":"https://orcid.org/0009-0001-1806-0058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Lai","raw_affiliation_strings":["NVIDIA Corporation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation,Shanghai,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4224,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85260449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"263","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9944000244140625,"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":0.9901999831199646,"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":0.7750151753425598},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.7283335328102112},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5943337678909302},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5877776741981506},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5856418609619141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4324970841407776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38825327157974243},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30935391783714294},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1221248209476471},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07928085327148438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750151753425598},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.7283335328102112},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5943337678909302},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5877776741981506},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5856418609619141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4324970841407776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38825327157974243},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30935391783714294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1221248209476471},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07928085327148438},{"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/slt61566.2024.10832173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832173","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1975113979","https://openalex.org/W1993660824","https://openalex.org/W2889048668","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2939757332","https://openalex.org/W2963263347","https://openalex.org/W2974231335","https://openalex.org/W2989143494","https://openalex.org/W3015615177","https://openalex.org/W3026041220","https://openalex.org/W3042170933","https://openalex.org/W3093579165","https://openalex.org/W3096122506","https://openalex.org/W3096615836","https://openalex.org/W3145132741","https://openalex.org/W3160201895","https://openalex.org/W3160475509","https://openalex.org/W3163135964","https://openalex.org/W3198429080","https://openalex.org/W3202037040","https://openalex.org/W4281770669","https://openalex.org/W4297841820","https://openalex.org/W4297841894","https://openalex.org/W4323066695","https://openalex.org/W4372260363","https://openalex.org/W4378105483","https://openalex.org/W4387800213","https://openalex.org/W4387892633","https://openalex.org/W4389518416","https://openalex.org/W4389600306","https://openalex.org/W4391021542","https://openalex.org/W4392737016","https://openalex.org/W4392903108","https://openalex.org/W4392903651","https://openalex.org/W4392903956","https://openalex.org/W4401609216","https://openalex.org/W6631190155","https://openalex.org/W6726497184","https://openalex.org/W6754473786","https://openalex.org/W6757817989","https://openalex.org/W6767671539","https://openalex.org/W6770506093","https://openalex.org/W6780815891","https://openalex.org/W6784614252","https://openalex.org/W6847363464","https://openalex.org/W6850218400","https://openalex.org/W6852909395","https://openalex.org/W6857131320","https://openalex.org/W6857428954","https://openalex.org/W6858893317","https://openalex.org/W6862616779","https://openalex.org/W6871033545"],"related_works":["https://openalex.org/W2771594921","https://openalex.org/W2432897346","https://openalex.org/W2181336723","https://openalex.org/W4389976243","https://openalex.org/W3158134258","https://openalex.org/W3138119129","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2974240475","https://openalex.org/W4404555432"],"abstract_inverted_index":{"Code-switching":[0],"(CS)":[1],"phenomenon":[2],"occurs":[3],"when":[4,54,176],"words":[5],"or":[6],"phrases":[7],"from":[8],"different":[9],"languages":[10],"are":[11],"alternated":[12],"in":[13],"a":[14,49,66],"single":[15],"sentence.":[16],"Due":[17],"to":[18,37,56,75,89],"data":[19,47,58,101,179],"scarcity,":[20],"building":[21],"an":[22],"effective":[23],"CS":[24,57,137,152],"Automatic":[25],"Speech":[26],"Recognition":[27],"(ASR)":[28],"system":[29],"remains":[30],"challenging.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,64,80,156],"propose":[36],"enhance":[38],"CS-ASR":[39,77],"systems":[40],"by":[41],"utilizing":[42],"rich":[43],"unsupervised":[44,115],"monolingual":[45,100,178],"speech":[46],"within":[48],"semi-supervised":[50,132],"learning":[51,133],"framework,":[52],"particularly":[53],"access":[55],"is":[59],"limited.":[60],"To":[61],"achieve":[62,173],"this,":[63],"establish":[65],"general":[67],"paradigm":[68],"for":[69,99,135],"applying":[70],"noisy":[71],"student":[72],"training":[73],"(NST)":[74],"the":[76,82,91,111,136,146,151,159,177],"task.":[78],"Specifically,":[79],"introduce":[81],"LLM-Filter,":[83],"which":[84],"leverages":[85],"well-designed":[86],"prompt":[87],"templates":[88],"activate":[90],"correction":[92],"capability":[93],"of":[94,161],"large":[95],"language":[96],"models":[97],"(LLMs)":[98],"selection":[102],"and":[103,114,117,131,166],"pseudo-labels":[104],"refinement":[105],"during":[106],"NST.":[107],"Our":[108],"experiments":[109],"on":[110,150,163],"supervised":[112,130],"ASRU-CS":[113],"AISHELL-2":[116],"LibriSpeech":[118],"datasets":[119],"show":[120],"that":[121,168],"our":[122,169],"method":[123,170],"not":[124],"only":[125],"achieves":[126],"significant":[127],"improvements":[128],"over":[129],"baselines":[134],"task,":[138],"but":[139],"also":[140],"attains":[141],"better":[142],"performance":[143],"compared":[144],"with":[145],"fully-supervised":[147],"oracle":[148],"upper-bound":[149],"English":[153],"part.":[154],"Additionally,":[155],"further":[157],"investigate":[158],"influence":[160],"accent":[162],"AESRC":[164],"dataset":[165],"demonstrate":[167],"can":[171],"get":[172],"additional":[174],"benefits":[175],"contains":[180],"relevant":[181],"linguistic":[182],"characteristic.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}