{"id":"https://openalex.org/W4406461820","doi":"https://doi.org/10.1109/slt61566.2024.10832326","title":"Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection","display_name":"Enhancing Code-Switching ASR Leveraging Non-Peaky CTC Loss and Deep Language Posterior Injection","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461820","doi":"https://doi.org/10.1109/slt61566.2024.10832326"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832326","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/A5102105085","display_name":"Tzu\u2010Ting Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tzu-Ting Yang","raw_affiliation_strings":["National Taiwan Normal University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041665750","display_name":"Hsin\u2010Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Wei Wang","raw_affiliation_strings":["National Taiwan Normal University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411058","display_name":"Yicheng Wang","orcid":"https://orcid.org/0009-0004-5670-0054"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Cheng Wang","raw_affiliation_strings":["National Taiwan Normal University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009731825","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["National Taiwan Normal University,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taipei,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102105085"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23178121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9919000267982483,"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":0.9757999777793884,"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":0.7563812732696533},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5544292330741882},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.5187473297119141},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42288678884506226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3904009461402893},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35676679015159607},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12382510304450989},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.07683497667312622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563812732696533},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5544292330741882},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.5187473297119141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42288678884506226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3904009461402893},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35676679015159607},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12382510304450989},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.07683497667312622},{"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/slt61566.2024.10832326","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832326","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W1494198834","https://openalex.org/W2073006259","https://openalex.org/W2153433699","https://openalex.org/W2603415636","https://openalex.org/W2884975363","https://openalex.org/W2939069254","https://openalex.org/W2963242190","https://openalex.org/W3042170933","https://openalex.org/W3093579165","https://openalex.org/W3096122506","https://openalex.org/W3097306574","https://openalex.org/W3097882114","https://openalex.org/W3160201895","https://openalex.org/W3160525311","https://openalex.org/W3162249256","https://openalex.org/W3167895882","https://openalex.org/W3197140813","https://openalex.org/W3204687321","https://openalex.org/W4281770669","https://openalex.org/W4285780592","https://openalex.org/W4297841499","https://openalex.org/W4372269995","https://openalex.org/W4372346832","https://openalex.org/W4385822407","https://openalex.org/W4385823039","https://openalex.org/W4392902746","https://openalex.org/W4392902865","https://openalex.org/W4392903651","https://openalex.org/W4400615884","https://openalex.org/W6780815891","https://openalex.org/W6784614252","https://openalex.org/W6796656850","https://openalex.org/W6839023126","https://openalex.org/W6841262374","https://openalex.org/W6846488704"],"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/W3204019825"],"abstract_inverted_index":{"Code-switching\u2014where":[0],"multilingual":[1],"speakers":[2],"alternately":[3],"switch":[4],"between":[5,121],"languages":[6,42],"during":[7],"conversations\u2014still":[8],"poses":[9],"significant":[10,48],"challenges":[11],"to":[12,21,36,47,73,98,117,156],"end-to-end":[13],"(E2E)":[14],"automatic":[15],"speech":[16],"recognition":[17],"(ASR)":[18],"systems":[19,34],"due":[20],"phenomena":[22],"of":[23,41,69,87,104,113,153],"both":[24],"acoustic":[25],"and":[26,124],"semantic":[27],"confusion.":[28],"This":[29],"issue":[30],"arises":[31],"because":[32],"ASR":[33,94],"struggle":[35],"handle":[37],"the":[38,70,84,92,102,111,131,142,151,154],"rapid":[39],"alternation":[40],"effectively,":[43],"which":[44],"often":[45],"leads":[46],"performance":[49],"degradation.":[50],"Our":[51],"main":[52],"contributions":[53],"are":[54,96],"at":[55],"least":[56],"threefold:":[57],"First,":[58],"we":[59,109,134],"incorporate":[60],"language":[61,80,88,106,115],"identification":[62],"(LID)":[63],"information":[64],"into":[65],"several":[66],"intermediate":[67],"layers":[68],"encoder,":[71],"aiming":[72],"enrich":[74],"output":[75],"embeddings":[76],"with":[77],"more":[78,99],"detailed":[79],"information.":[81],"Secondly,":[82],"through":[83],"novel":[85],"application":[86],"boundary":[89],"alignment":[90],"loss,":[91],"subsequent":[93],"modules":[95],"enabled":[97],"effectively":[100],"utilize":[101],"knowledge":[103],"internal":[105],"posteriors.":[107],"Third,":[108],"explore":[110],"feasibility":[112],"using":[114],"posteriors":[116],"facilitate":[118],"deep":[119],"interaction":[120],"shared":[122],"encoder":[123,155],"language-specific":[125],"encoders.":[126],"Through":[127],"comprehensive":[128],"experiments":[129],"on":[130],"SEAME":[132],"corpus,":[133],"have":[135],"verified":[136],"that":[137],"our":[138],"proposed":[139],"method":[140],"outperforms":[141],"prior-art":[143],"method,":[144],"disentangle":[145],"based":[146],"mixture-of-experts":[147],"(D-MoE),":[148],"further":[149],"enhancing":[150],"acuity":[152],"languages.":[157]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}