{"id":"https://openalex.org/W4415432728","doi":"https://doi.org/10.21437/interspeech.2025-2549","title":"Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning","display_name":"Adapting Whisper for Parameter-efficient Code-Switching Speech Recognition via Soft Prompt Tuning","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432728","doi":"https://doi.org/10.21437/interspeech.2025-2549"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2549","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2549","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/2506.21576","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/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":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071426656","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6212-5448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Li","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":0.258711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5203","last_page":"5207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9674999713897705,"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":0.9674999713897705,"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/T10860","display_name":"Speech and Audio Processing","score":0.9549999833106995,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/training-set","display_name":"Training set","score":0.5241000056266785},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4787999987602234},{"id":"https://openalex.org/keywords/soft-computing","display_name":"Soft computing","score":0.37369999289512634},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.35679998993873596},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.35519999265670776},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2937000095844269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382999897003174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6460000276565552},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4787999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C140073362","wikidata":"https://www.wikidata.org/wiki/Q738759","display_name":"Soft computing","level":3,"score":0.37369999289512634},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-2549","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2549","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:2506.21576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21576","pdf_url":"https://arxiv.org/pdf/2506.21576","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:50734107","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100933508","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:2506.21576","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21576","pdf_url":"https://arxiv.org/pdf/2506.21576","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":{"Large-scale":[0],"multilingual":[1],"ASR":[2,42],"models":[3],"like":[4],"Whisper":[5,62],"excel":[6],"in":[7,13,124],"high-resource":[8],"settings":[9],"but":[10],"face":[11],"challenges":[12],"low-resource":[14],"scenarios,":[15],"such":[16],"as":[17],"rare":[18],"languages":[19],"and":[20,27,59,72,83,102,116],"code-switching":[21],"(CS),":[22],"due":[23],"to":[24,39,69,75,131],"computational":[25],"costs":[26],"catastrophic":[28],"forgetting.":[29],"We":[30,47],"explore":[31],"Soft":[32],"Prompt":[33],"Tuning":[34],"(SPT),":[35],"a":[36,92],"parameter-efficient":[37],"method":[38],"enhance":[40],"CS":[41,125],"while":[43],"preserving":[44],"prior":[45],"knowledge.":[46],"evaluate":[48],"two":[49],"strategies:":[50],"(1)":[51],"full":[52],"fine-tuning":[53],"(FFT)":[54],"of":[55,94],"both":[56],"soft":[57,86],"prompts":[58],"the":[60,100,111],"entire":[61],"model,":[63],"demonstrating":[64],"improved":[65],"cross-lingual":[66],"capabilities":[67],"compared":[68],"traditional":[70],"methods,":[71],"(2)":[73],"adhering":[74],"SPT's":[76],"original":[77],"design":[78],"by":[79],"freezing":[80],"model":[81],"parameters":[82],"only":[84],"training":[85],"prompts.":[87],"Additionally,":[88],"we":[89],"introduce":[90],"SPT4ASR,":[91],"combination":[93],"different":[95],"SPT":[96,114],"variants.":[97],"Experiments":[98],"on":[99,136],"SEAME":[101],"ASRU2019":[103],"datasets":[104],"show":[105],"that":[106],"deep":[107],"prompt":[108],"tuning":[109],"is":[110],"most":[112],"effective":[113],"approach,":[115],"our":[117],"SPT4ASR":[118],"methods":[119],"achieve":[120],"further":[121],"error":[122],"reductions":[123],"ASR,":[126],"maintaining":[127],"parameter":[128],"efficiency":[129],"similar":[130],"LoRA,":[132],"without":[133],"degrading":[134],"performance":[135],"existing":[137],"languages.":[138]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-23T00:00:00"}