{"id":"https://openalex.org/W4408352399","doi":"https://doi.org/10.1109/icassp49660.2025.10889526","title":"Leveraging IPA and Articulatory Features as Effective Inductive Biases for Multilingual ASR Training","display_name":"Leveraging IPA and Articulatory Features as Effective Inductive Biases for Multilingual ASR Training","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352399","doi":"https://doi.org/10.1109/icassp49660.2025.10889526"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889526","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/A5100350945","display_name":"Jaeyoung Lee","orcid":"https://orcid.org/0000-0003-1211-688X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jaeyoung Lee","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9452999830245972,"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":0.9452999830245972,"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":0.7505273818969727},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6840162873268127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.528670072555542},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4948088526725769},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38809022307395935},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37608814239501953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505273818969727},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6840162873268127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.528670072555542},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4948088526725769},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38809022307395935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37608814239501953},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889526","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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"},{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2116648050","https://openalex.org/W2127141656","https://openalex.org/W2140372979","https://openalex.org/W2262393948","https://openalex.org/W2963431393","https://openalex.org/W2963597470","https://openalex.org/W2972557594","https://openalex.org/W2998284473","https://openalex.org/W3164045210","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4224629880","https://openalex.org/W4285144981","https://openalex.org/W4319862480","https://openalex.org/W4372259817","https://openalex.org/W4385823357","https://openalex.org/W4392903557","https://openalex.org/W6731852758","https://openalex.org/W6771467084","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W3204019825","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0,33,78],"recent":[1],"advancements":[2],"in":[3,109],"end-to-end":[4],"ASR,":[5],"large-scale":[6],"self-supervised":[7],"or":[8,69],"weakly":[9],"supervised":[10],"models":[11],"have":[12],"achieved":[13,104],"a":[14,84,105],"significant":[15],"milestone.":[16],"However,":[17],"it":[18],"remains":[19],"challenging":[20],"to":[21,28,42,64],"train":[22],"consistently":[23],"high-performing":[24],"multilingual":[25,43],"models,":[26],"transferable":[27],"languages":[29,95],"without":[30],"much":[31],"resource.":[32],"this":[34],"study,":[35],"we":[36],"propose":[37],"embedding":[38],"universal":[39,53],"phonological":[40],"knowledge":[41],"ASR":[44],"by":[45],"predicting":[46,72],"international":[47],"phonetic":[48],"alphabet":[49],"(IPA)":[50],"targets":[51,74],"and":[52],"articulatory":[54],"features":[55],"alongside":[56],"primary":[57],"grapheme":[58,73],"targets.":[59],"These":[60],"additions":[61],"are":[62],"expected":[63],"provide":[65],"effective":[66],"inductive":[67],"bias":[68],"regularization":[70],"for":[71],"across":[75,93],"various":[76],"languages.":[77],"the":[79,97],"experiments,":[80],"which":[81],"involve":[82],"fine-tuning":[83],"pre-trained":[85],"XLS-R":[86],"model":[87],"using":[88],"10,400":[89],"hours":[90],"of":[91],"data":[92],"120":[94],"from":[96],"Common":[98],"Voice":[99],"corpus,":[100],"our":[101],"proposed":[102],"method":[103],"6.81%":[106],"relative":[107],"reduction":[108],"character":[110],"error":[111],"rate.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}