{"id":"https://openalex.org/W7148506573","doi":"https://doi.org/10.1109/asru65441.2025.11433848","title":"A correlation-permutation approach for speech-music encoders model merging","display_name":"A correlation-permutation approach for speech-music encoders model merging","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148506573","doi":"https://doi.org/10.1109/asru65441.2025.11433848"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11433848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433848","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":"https://openalex.org/A5092905575","display_name":"Fabian Ritter-Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fabian Ritter-Gutierrez","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083437044","display_name":"Yi\u2010Cheng Lin","orcid":"https://orcid.org/0000-0002-5130-5280"},"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":"Yi-Cheng Lin","raw_affiliation_strings":["National Taiwan University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021413708","display_name":"Jhm Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jeremy H.M Wong","raw_affiliation_strings":["Institute for Infocomm Research,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","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":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120309277","display_name":"Eng Siong Chng","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132795316","display_name":"Nancy F. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nancy F. Chen","raw_affiliation_strings":["Institute for Infocomm Research,Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research,Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5092905575"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.4346,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8737919,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T10860","display_name":"Speech and Audio Processing","score":0.3285999894142151,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.3285999894142151,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.3043999969959259,"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/T11309","display_name":"Music and Audio Processing","score":0.07720000296831131,"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/speech-coding","display_name":"Speech coding","score":0.5023999810218811},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.498199999332428},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.45239999890327454},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4465999901294708},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4325999915599823},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.41449999809265137},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.35179999470710754},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33009999990463257},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3278999924659729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6837999820709229},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5023999810218811},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4708000123500824},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4465999901294708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4325999915599823},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.313400000333786},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2806999981403351},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11433848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433848","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":[{"display_name":"Quality Education","score":0.4202567934989929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W63488022","https://openalex.org/W1494198834","https://openalex.org/W1904457459","https://openalex.org/W2052666245","https://openalex.org/W2133824856","https://openalex.org/W2134513193","https://openalex.org/W2135293965","https://openalex.org/W2146334809","https://openalex.org/W2164217305","https://openalex.org/W2557169239","https://openalex.org/W2946794439","https://openalex.org/W2972324944","https://openalex.org/W2972584841","https://openalex.org/W2981087920","https://openalex.org/W3045349544","https://openalex.org/W3094780479","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W4226380987","https://openalex.org/W4250482878","https://openalex.org/W4375869259","https://openalex.org/W4385822439","https://openalex.org/W4402112457","https://openalex.org/W4404783543","https://openalex.org/W4406462041","https://openalex.org/W4408356249","https://openalex.org/W4415433654","https://openalex.org/W4416513625","https://openalex.org/W7131784863","https://openalex.org/W7133238265"],"related_works":[],"abstract_inverted_index":{"Creating":[0],"a":[1,15,44,49,55,72],"unified":[2,16,128],"speech":[3,56,96],"and":[4],"music":[5,50,104],"model":[6,18,94,120],"requires":[7],"expensive":[8],"pre-training.":[9],"Model":[10],"merging":[11,25,66],"can":[12],"instead":[13],"create":[14],"audio":[17,129],"with":[19,54],"minimal":[20],"computational":[21],"expense.":[22],"However,":[23],"direct":[24],"is":[26],"challenging":[27],"when":[28],"the":[29,35,63,77,117,125],"models":[30,130],"are":[31],"not":[32],"aligned":[33],"in":[34,112],"weight":[36],"space.":[37],"Motivated":[38],"by":[39,82],"Git":[40],"Re-Basin,":[41],"we":[42],"introduce":[43],"correlation-permutation":[45],"approach":[46],"that":[47,75],"aligns":[48],"encoder\u2019s":[51],"internal":[52],"layers":[53],"encoder.":[57],"We":[58],"extend":[59],"previous":[60],"work":[61,123],"to":[62,116],"case":[64],"of":[65,87,109,127],"transformer":[67],"layers.":[68],"The":[69,92],"method":[70,100],"computes":[71],"permutation":[73],"matrix":[74],"maximizes":[76],"model\u2019s":[78],"features-wise":[79],"cross-correlations":[80],"layer":[81],"layer,":[83],"enabling":[84],"effective":[85],"fusion":[86],"these":[88],"otherwise":[89],"disjoint":[90],"models.":[91],"merged":[93],"retains":[95],"capabilities":[97],"through":[98],"this":[99],"while":[101],"significantly":[102],"enhancing":[103],"performance,":[105],"achieving":[106],"an":[107],"improvement":[108],"14.83":[110],"points":[111],"average":[113],"score":[114],"compared":[115],"linear":[118],"interpolation":[119],"merging.":[121],"This":[122],"allows":[124],"creation":[126],"from":[131],"independently":[132],"trained":[133],"encoders.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}