{"id":"https://openalex.org/W4408353448","doi":"https://doi.org/10.1109/icassp49660.2025.10890363","title":"Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling","display_name":"Enhancing Multilingual ASR for Unseen Languages via Language Embedding Modeling","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353448","doi":"https://doi.org/10.1109/icassp49660.2025.10890363"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890363","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":"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/A5073674747","display_name":"Shao-Syuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Syuan Huang","raw_affiliation_strings":["National Taiwan University,Computer Science and Information Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103339163","display_name":"Kuan-Po Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Po Huang","raw_affiliation_strings":["National Taiwan University, AICS ASUS,Computer Science and Information Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, AICS ASUS,Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018050919","display_name":"Andy T. Liu","orcid":"https://orcid.org/0000-0002-2502-3992"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Andy T. Liu","raw_affiliation_strings":["National Taiwan University, AICS ASUS,Computer Science and Information Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, AICS ASUS,Computer Science and Information Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Electrical Engineering,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Electrical Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":2.9572,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89097621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9833999872207642,"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":0.9833999872207642,"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":0.9682999849319458,"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":0.967199981212616,"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":0.8046250343322754},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.702194333076477},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6364120244979858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5157766342163086},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4972746670246124},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4323011636734009},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3512897789478302}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8046250343322754},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.702194333076477},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6364120244979858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5157766342163086},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4972746670246124},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4323011636734009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3512897789478302},{"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/icassp49660.2025.10890363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890363","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5299999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2964309797","https://openalex.org/W3016010032","https://openalex.org/W3198429080","https://openalex.org/W3213029956","https://openalex.org/W4385822439","https://openalex.org/W4385822890","https://openalex.org/W4391021545","https://openalex.org/W4401609216","https://openalex.org/W4402111244","https://openalex.org/W4406461631","https://openalex.org/W6687566353","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2419146053","https://openalex.org/W4388890789","https://openalex.org/W2088247287","https://openalex.org/W2963903416"],"abstract_inverted_index":{"Multilingual":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"aims":[5],"to":[6,31,80],"recognize":[7],"and":[8,25],"transcribe":[9],"speech":[10],"from":[11],"multiple":[12],"languages":[13,68,143],"within":[14],"a":[15,20,74,113],"single":[16],"system.":[17],"By":[18],"leveraging":[19],"vast":[21],"amount":[22],"of":[23,39,84,102],"data":[24],"incorporating":[26],"language":[27,92,103],"tokens":[28,104],"as":[29,94],"prefixes":[30],"guide":[32],"the":[33,40,64,96,100,121,133,145],"recognition":[34],"process,":[35],"Whisper":[36,50,85],"is":[37],"one":[38],"most":[41],"advanced":[42],"multilingual":[43,146],"ASR":[44,82,147],"models.":[45],"However,":[46],"despite":[47],"its":[48,60],"success,":[49],"struggles":[51],"with":[52],"unseen":[53,87,142],"languages,":[54],"which":[55],"are":[56],"not":[57],"included":[58],"in":[59,86,144],"pre-training.":[61],"Motivated":[62],"by":[63],"observation":[65],"that":[66,76,116,131],"many":[67],"share":[69],"linguistic":[70],"characteristics,":[71],"we":[72,110],"propose":[73],"method":[75],"exploits":[77],"these":[78],"relationships":[79],"improve":[81],"performance":[83],"languages.":[88],"With":[89],"Whisper\u2019s":[90],"predicted":[91],"probabilities":[93],"weight,":[95],"approach":[97,115],"weighted":[98,122],"sums":[99],"embeddings":[101],".":[105],"Based":[106],"on":[107],"this":[108],"method,":[109],"also":[111],"develop":[112],"predictor-based":[114],"supports":[117],"our":[118],"assumption":[119],"about":[120],"sum":[123],"method.":[124],"Our":[125],"proposed":[126],"methods":[127],"demonstrate":[128],"substantial":[129],"improvements":[130],"outperform":[132],"baseline":[134],"approaches,":[135],"providing":[136],"an":[137],"effective":[138],"solution":[139],"for":[140],"addressing":[141],"task.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}