{"id":"https://openalex.org/W7148488097","doi":"https://doi.org/10.1109/asru65441.2025.11434624","title":"SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR","display_name":"SSVD: Structured SVD for Parameter-Efficient Fine-Tuning and Benchmarking under Domain Shift in ASR","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148488097","doi":"https://doi.org/10.1109/asru65441.2025.11434624"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"display_name":"Pu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pu Wang","raw_affiliation_strings":["KU Leuven,Department of Electrical Engineering,Leuven,Belgium"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shinji Watanabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute Carnegie Mellon University,Pittsburgh,PA,USA"],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Hugo Van Hamme","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Van Hamme","raw_affiliation_strings":["KU Leuven,Department of Electrical Engineering,Leuven,Belgium"],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92937921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8937000036239624,"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":0.8937000036239624,"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":0.0272000003606081,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.02319999970495701,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8532000184059143},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6230999827384949},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.5516999959945679},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5493000149726868},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5223000049591064},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4796000123023987},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.46959999203681946},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8532000184059143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592999935150146},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6230999827384949},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.5516999959945679},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5184000134468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034999847412109},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4796000123023987},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39590001106262207},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3393000066280365},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4654017686843872,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2004026774","https://openalex.org/W2962780374","https://openalex.org/W3176828726","https://openalex.org/W4205991051","https://openalex.org/W4297841643","https://openalex.org/W4319862255","https://openalex.org/W4362696744","https://openalex.org/W4385245566","https://openalex.org/W4391021675","https://openalex.org/W4392903650","https://openalex.org/W4392908891","https://openalex.org/W4392909818","https://openalex.org/W4402111442","https://openalex.org/W4402111558","https://openalex.org/W4402112032","https://openalex.org/W4402112108","https://openalex.org/W4402112192","https://openalex.org/W4402115918","https://openalex.org/W4404518524","https://openalex.org/W4415795259","https://openalex.org/W4415798154","https://openalex.org/W7131817459"],"related_works":[],"abstract_inverted_index":{"Parameter-efficient":[0],"fine-tuning":[1],"(PEFT)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6],"scalable":[7],"solution":[8],"for":[9,36],"adapting":[10],"large":[11],"foundation":[12],"models.":[13],"While":[14],"low-rank":[15],"adaptation":[16,89],"(LoRA)":[17],"is":[18],"widely":[19],"used":[20],"in":[21,44,123],"speech":[22,103,108],"applications,":[23],"its":[24],"state-of-the-art":[25],"variants,":[26],"e.g.,":[27],"VeRA,":[28],"DoRA,":[29],"PiSSA,":[30],"and":[31,38,53,94,109,128],"SVFT,":[32],"are":[33,121],"developed":[34],"mainly":[35],"language":[37],"vision":[39],"tasks,":[40,105],"with":[41,90],"limited":[42],"validation":[43],"speech.":[45],"This":[46,84],"work":[47],"presents":[48],"the":[49],"first":[50],"comprehensive":[51],"integration":[52],"benchmarking":[54],"of":[55],"these":[56],"PEFT":[57],"methods":[58,100],"within":[59],"ESPnet.":[60],"We":[61,97],"further":[62],"introduce":[63],"structured":[64],"SVDguided":[65],"(SSVD)":[66],"fine-tuning,":[67],"which":[68],"selectively":[69],"rotates":[70],"input-associated":[71],"right":[72],"singular":[73],"vectors":[74,78],"while":[75],"keeping":[76],"output-associated":[77],"fixed":[79],"to":[80,117,125],"preserve":[81],"semantic":[82],"mappings.":[83],"design":[85],"enables":[86],"robust":[87],"domain":[88],"minimal":[91],"trainable":[92],"parameters":[93],"improved":[95],"efficiency.":[96],"evaluate":[98],"all":[99],"on":[101],"domain-shifted":[102],"recognition":[104],"including":[106],"child":[107],"dialectal":[110],"variation,":[111],"across":[112],"model":[113],"scales":[114],"from":[115],"0.1B":[116],"2B.":[118],"All":[119],"implementations":[120],"released":[122],"ESPnet":[124],"support":[126],"reproducibility":[127],"future":[129],"work.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-12-10T00:00:00"}