{"id":"https://openalex.org/W4372260195","doi":"https://doi.org/10.1109/icassp49357.2023.10096568","title":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","display_name":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260195","doi":"https://doi.org/10.1109/icassp49357.2023.10096568"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020376803","display_name":"Chao-Han Huck Yang","orcid":"https://orcid.org/0000-0003-2879-8811"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao-Han Huck Yang","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050344371","display_name":"Pin\u2010Yu Chen","orcid":"https://orcid.org/0000-0003-1039-8369"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin-Yu Chen","raw_affiliation_strings":["IBM Research,NY,USA","IBM Research, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research,NY,USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"IBM Research, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048454242","display_name":"Alexander Lerch","orcid":"https://orcid.org/0000-0001-6319-578X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Lerch","raw_affiliation_strings":["Georgia Institute of Technology,Atlanta,GA,USA","Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5005504900"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":3.7726,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.94291204,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11309","display_name":"Music and Audio Processing","score":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.7919096946716309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580018937587738},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5704219937324524},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.564423680305481},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5364388227462769},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5066822171211243},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4810662269592285},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.47303053736686707},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.43198898434638977},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4293655753135681},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41765856742858887},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4171365201473236},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4165458381175995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36736515164375305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35595130920410156},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32067710161209106}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919096946716309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580018937587738},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5704219937324524},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.564423680305481},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5364388227462769},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5066822171211243},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4810662269592285},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.47303053736686707},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.43198898434638977},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4293655753135681},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41765856742858887},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4171365201473236},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4165458381175995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36736515164375305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35595130920410156},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32067710161209106},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096568","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1945616565","https://openalex.org/W2108598243","https://openalex.org/W2117539524","https://openalex.org/W2512971201","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2794150026","https://openalex.org/W2797583228","https://openalex.org/W2888641632","https://openalex.org/W2896457183","https://openalex.org/W2919115771","https://openalex.org/W2939574508","https://openalex.org/W2962904371","https://openalex.org/W2970508906","https://openalex.org/W2972737975","https://openalex.org/W3029858316","https://openalex.org/W3035742266","https://openalex.org/W3155776249","https://openalex.org/W3172443934","https://openalex.org/W3174784402","https://openalex.org/W3180663620","https://openalex.org/W3196974791","https://openalex.org/W4287556475","https://openalex.org/W4287635193","https://openalex.org/W4287802874","https://openalex.org/W4298312696","https://openalex.org/W4300957348","https://openalex.org/W6640425456","https://openalex.org/W6752946794","https://openalex.org/W6755207826","https://openalex.org/W6763509872","https://openalex.org/W6768465061","https://openalex.org/W6778572914","https://openalex.org/W6779945560","https://openalex.org/W6784260069","https://openalex.org/W6794667172","https://openalex.org/W6796456916","https://openalex.org/W6798597329"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W3095487414","https://openalex.org/W4288048773","https://openalex.org/W2901026139"],"abstract_inverted_index":{"Transfer":[0],"learning":[1],"(TL)":[2],"approaches":[3],"have":[4],"shown":[5],"promising":[6],"results":[7,114],"when":[8],"handling":[9],"tasks":[10],"with":[11,29],"limited":[12],"training":[13],"data.":[14,32],"However,":[15],"considerable":[16],"memory":[17],"and":[18],"computational":[19],"resources":[20],"are":[21],"often":[22],"required":[23],"for":[24,41,46,83],"fine-tuning":[25],"pre-trained":[26,43,64,81,120],"neural":[27,118],"networks":[28],"target":[30,72],"domain":[31,69,73],"In":[33,86],"this":[34,132],"work,":[35],"we":[36,94],"introduce":[37],"a":[38,63,67,71,79,117,147],"novel":[39],"method":[40],"leveraging":[42],"speech":[44],"models":[45,82],"low-resource":[47],"music":[48,127],"classification":[49,129,150],"based":[50],"on":[51,121,146],"the":[52,76,89],"concept":[53],"of":[54,78],"Neural":[55],"Model":[56],"Reprogramming":[57],"(NMR).":[58],"NMR":[59,139],"aims":[60],"at":[61],"re-purposing":[62],"model":[65,119],"from":[66],"source":[68],"to":[70,88,102,105],"by":[74,130],"modifying":[75],"input":[77,107],"frozen":[80],"cross-modal":[84],"adaptation.":[85],"addition":[87],"known,":[90],"input-independent,":[91],"re-programming":[92],"method,":[93],"propose":[95],"an":[96],"new":[97],"reprogramming":[98,133],"paradigm:":[99],"Input-dependent":[100,138],"NMR,":[101],"increase":[103],"adaptability":[104],"complex":[106],"data":[108],"such":[109],"as":[110],"musical":[111],"audio.":[112],"Experimental":[113],"suggest":[115],"that":[116],"large-scale":[122],"datasets":[123],"can":[124],"successfully":[125],"perform":[126],"genre":[128,149],"using":[131],"method.":[134],"The":[135],"two":[136],"proposed":[137],"TL":[140,144],"methods":[141,145],"outperform":[142],"fine-tuning-based":[143],"small":[148],"dataset.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":10}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}