{"id":"https://openalex.org/W4385477895","doi":"https://doi.org/10.1109/icasspw59220.2023.10193076","title":"Unfused: Unsupervised Finetuning Using Self Supervised Distillation","display_name":"Unfused: Unsupervised Finetuning Using Self Supervised Distillation","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385477895","doi":"https://doi.org/10.1109/icasspw59220.2023.10193076"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193076","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5027141199","display_name":"Ashish Seth","orcid":"https://orcid.org/0000-0003-1580-897X"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Seth","raw_affiliation_strings":["IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.08622306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","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":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8077978491783142},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.799686849117279},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7145348787307739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6462458968162537},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5829511284828186},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.574216365814209},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.48215433955192566},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4546726644039154},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.44105011224746704},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4328407347202301},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4297754764556885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077978491783142},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.799686849117279},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7145348787307739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6462458968162537},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5829511284828186},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.574216365814209},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.48215433955192566},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4546726644039154},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.44105011224746704},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4328407347202301},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4297754764556885},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193076","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw59220.2023.10193076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2146334809","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2797583228","https://openalex.org/W2883595988","https://openalex.org/W2896457183","https://openalex.org/W2982223350","https://openalex.org/W3034368386","https://openalex.org/W3035524453","https://openalex.org/W3036224891","https://openalex.org/W3036601975","https://openalex.org/W3038899388","https://openalex.org/W3088092535","https://openalex.org/W3138154797","https://openalex.org/W3162391496","https://openalex.org/W3197580070","https://openalex.org/W3201143670","https://openalex.org/W3203140070","https://openalex.org/W3206649123","https://openalex.org/W3209059054","https://openalex.org/W4205689591","https://openalex.org/W4224917447","https://openalex.org/W4225713393","https://openalex.org/W4283215442","https://openalex.org/W4293370787","https://openalex.org/W4295723153","https://openalex.org/W4303649027","https://openalex.org/W4372340876","https://openalex.org/W6736723571","https://openalex.org/W6755207826","https://openalex.org/W6779997284","https://openalex.org/W6780218876","https://openalex.org/W6780379688","https://openalex.org/W6783591283","https://openalex.org/W6802796180","https://openalex.org/W6839130774","https://openalex.org/W6845692261"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W915438175","https://openalex.org/W4230315250"],"abstract_inverted_index":{"In":[0,156],"this":[1,177],"paper,":[2],"we":[3,40,73,104,121],"introduce":[4],"UnFuSeD,":[5,120],"a":[6,32,37,61,99,144,179],"novel":[7,62,145],"approach":[8],"to":[9,44,77,95,148,175],"leverage":[10,149],"self-supervised":[11,33,63],"learning":[12,64],"and":[13,137,142],"reduce":[14],"the":[15,42,51,87,109,123,139,163,184,189],"need":[16],"for":[17,23,47,152],"large":[18],"amounts":[19],"of":[20,186],"labeled":[21],"data":[22],"audio":[24,70,154],"classification.":[25,155],"Unlike":[26],"prior":[27],"works,":[28],"which":[29,103,135],"directly":[30],"fine-tune":[31,138],"pre-trained":[34],"encoder":[35,43,59,76,111],"on":[36,67,80,98,114,162],"target":[38,82,116],"dataset,":[39],"use":[41,74],"generate":[45,78],"pseudo-labels":[46,79,91],"unsupervised":[48,106],"fine-tuning":[49,53],"before":[50],"actual":[52],"step.":[54],"We":[55,193],"first":[56,124],"train":[57],"an":[58,68],"using":[60],"algorithm":[65],"(SSL)":[66],"unlabeled":[69],"dataset.":[71,118],"Then,":[72],"that":[75,126],"our":[81,115,169,196],"task":[83,117],"dataset":[84],"via":[85],"clustering":[86],"extracted":[88],"representations.":[89],"These":[90],"are":[92],"then":[93],"used":[94],"guide":[96],"self-distillation":[97],"randomly":[100],"initialized":[101],"model,":[102],"call":[105],"fine-tuning.":[107],"Finally,":[108],"resultant":[110],"is":[112],"fine-tuned":[113],"Through":[119],"propose":[122],"system":[125,147],"moves":[127],"away":[128],"from":[129],"generic":[130],"SSL":[131,150],"paradigms":[132],"in":[133,183],"literature,":[134],"pretrain":[136],"same":[140],"encoder,":[141],"presents":[143],"self-distillation-based":[146],"pre-training":[151],"low-resource":[153],"practice,":[157],"UnFuSeD":[158,172],"achieves":[159],"state-of-the-art":[160,191],"results":[161],"LAPE":[164],"Benchmark,":[165],"significantly":[166],"outperforming":[167],"all":[168,195],"baselines.":[170],"Additionally,":[171],"allows":[173],"us":[174],"achieve":[176],"at":[178],"$\\approx":[180],"40$%":[181],"reduction":[182],"number":[185],"parameters":[187],"over":[188],"previous":[190],"system.":[192],"make":[194],"codes":[197],"publicly":[198],"available1.1https://github.com/Sreyan88/LAPE":[199]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}