{"id":"https://openalex.org/W4415433023","doi":"https://doi.org/10.21437/interspeech.2025-1875","title":"Language-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR","display_name":"Language-Aware Prompt Tuning for Parameter-Efficient Seamless Language Expansion in Multilingual ASR","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433023","doi":"https://doi.org/10.21437/interspeech.2025-1875"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1875","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.21577","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102793453","display_name":"Hongli Yang","orcid":"https://orcid.org/0009-0008-7605-655X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongli Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064381421","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0003-1748-1245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093817","display_name":"Ayiduosi Tuohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayiduosi Tuohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5114025990","display_name":"Yizhou Peng","orcid":"https://orcid.org/0000-0002-5718-570X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25928035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1133","last_page":"1137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.953000009059906,"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":0.953000009059906,"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":0.949999988079071,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9330999851226807,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6204000115394592},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.57669997215271},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5758000016212463},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4970000088214874},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3939000070095062},{"id":"https://openalex.org/keywords/constructed-language","display_name":"Constructed language","score":0.36730000376701355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8535000085830688},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6204000115394592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501800000667572},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C94922259","wikidata":"https://www.wikidata.org/wiki/Q33215","display_name":"Constructed language","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-1875","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1875","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.21577","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21577","pdf_url":"https://arxiv.org/pdf/2506.21577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50734108","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100933509","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.21577","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21577","pdf_url":"https://arxiv.org/pdf/2506.21577","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,115],"multilingual":[3,126],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"have":[8],"been":[9],"driven":[10],"by":[11,111],"large-scale":[12],"end-to-end":[13],"models":[14,128],"like":[15],"Whisper.":[16],"However,":[17],"challenges":[18],"such":[19],"as":[20],"language":[21,116],"interference":[22],"and":[23,56,61,75,91,106,113],"expanding":[24],"to":[25,52,72],"unseen":[26],"languages":[27,99],"(language":[28],"expansion)":[29],"without":[30],"degrading":[31],"performance":[32],"persist.":[33],"This":[34],"paper":[35],"addresses":[36],"these":[37],"with":[38,129],"three":[39,98],"contributions:":[40],"1)":[41],"Entire":[42,104],"Soft":[43],"Prompt":[44,65],"Tuning":[45,66],"(Entire":[46],"SPT),":[47],"which":[48,68],"applies":[49],"soft":[50],"prompts":[51],"both":[53],"the":[54],"encoder":[55],"decoder,":[57],"enhancing":[58],"feature":[59],"extraction":[60],"decoding;":[62],"2)":[63],"Language-Aware":[64],"(LAPT),":[67],"leverages":[69],"cross-lingual":[70],"similarities":[71],"encode":[73],"shared":[74],"language-specific":[76],"features":[77],"using":[78],"lightweight":[79],"prompt":[80],"matrices;":[81],"3)":[82],"SPT-Whisper,":[83],"a":[84],"toolkit":[85],"that":[86,103],"integrates":[87],"SPT":[88,105,110],"into":[89],"Whisper":[90],"enables":[92],"efficient":[93,122],"continual":[94],"learning.":[95],"Experiments":[96],"across":[97],"from":[100],"FLEURS":[101],"demonstrate":[102],"LAPT":[107],"outperform":[108],"Decoder":[109],"5.0%":[112],"16.0%":[114],"expansion":[117],"tasks,":[118],"respectively,":[119],"providing":[120],"an":[121],"solution":[123],"for":[124],"dynamic,":[125],"ASR":[127],"minimal":[130],"computational":[131],"overhead.":[132]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-23T00:00:00"}