{"id":"https://openalex.org/W4372348584","doi":"https://doi.org/10.1109/icassp49357.2023.10096970","title":"SLICER: Learning Universal Audio Representations Using Low-Resource Self-Supervised Pre-Training","display_name":"SLICER: Learning Universal Audio Representations Using Low-Resource Self-Supervised Pre-Training","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348584","doi":"https://doi.org/10.1109/icassp49357.2023.10096970"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096970","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096970","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":"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/A5018932560","display_name":"Ashish Seth","orcid":"https://orcid.org/0000-0003-3100-9342"},"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":0.03479381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","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":0.9998000264167786,"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":0.9997000098228455,"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/spectrogram","display_name":"Spectrogram","score":0.7825925350189209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598094940185547},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6956440210342407},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6839957237243652},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6634296178817749},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6192747950553894},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6143574118614197},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5855754613876343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5553702116012573},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5499774813652039},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5319151282310486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5182833075523376},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.48661503195762634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4322187900543213},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3994535505771637}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7825925350189209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598094940185547},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6956440210342407},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6839957237243652},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6634296178817749},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6192747950553894},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6143574118614197},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5855754613876343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5553702116012573},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5499774813652039},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5319151282310486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5182833075523376},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.48661503195762634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4322187900543213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3994535505771637},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096970","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096970","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":[{"display_name":"Quality Education","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2146334809","https://openalex.org/W2606176153","https://openalex.org/W2726515241","https://openalex.org/W2765407302","https://openalex.org/W2797583228","https://openalex.org/W2883595988","https://openalex.org/W2896457183","https://openalex.org/W2982223350","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3144810982","https://openalex.org/W3162391496","https://openalex.org/W3197580070","https://openalex.org/W3201143670","https://openalex.org/W3206649123","https://openalex.org/W3209059054","https://openalex.org/W4205689591","https://openalex.org/W4225713393","https://openalex.org/W4293370787","https://openalex.org/W4295723153","https://openalex.org/W6736723571","https://openalex.org/W6740167877","https://openalex.org/W6752516136","https://openalex.org/W6755207826","https://openalex.org/W6769593479","https://openalex.org/W6779326418","https://openalex.org/W6780218876","https://openalex.org/W6783462664"],"related_works":["https://openalex.org/W2983142544","https://openalex.org/W2891059443","https://openalex.org/W4281663961","https://openalex.org/W3208888551","https://openalex.org/W4313561566","https://openalex.org/W3208386644","https://openalex.org/W4389832810","https://openalex.org/W4220682630","https://openalex.org/W3181622257","https://openalex.org/W3163146846"],"abstract_inverted_index":{"We":[0,96,118],"present":[1],"a":[2,42,51,98,145],"new":[3],"Self-Supervised":[4],"Learning":[5,77],"(SSL)":[6],"approach":[7],"to":[8,34,136],"pre-train":[9],"encoders":[10,108],"on":[11,152,172,185],"unlabeled":[12],"audio":[13,26,54],"data":[14,24,189],"that":[15,38],"reduces":[16],"the":[17,59,87,126,137,173],"need":[18],"for":[19,25,68,165],"large":[20,43],"amounts":[21],"of":[22,45,62,78,89,139],"labeled":[23],"and":[27,47,64,80,92,106,109,113,160],"speech":[28,46,70],"classification.":[29],"Our":[30],"primary":[31],"aim":[32],"is":[33],"learn":[35],"au-dio":[36],"representations":[37,103,121],"can":[39],"generalize":[40],"across":[41],"vari-ety":[44],"non-speech":[48],"tasks":[49],"in":[50],"low-resource":[52],"un-labeled":[53],"pre-training":[55],"setting.":[56,192],"Inspired":[57],"by":[58,123],"recent":[60],"success":[61],"clustering":[63,91],"contrasting":[65,93],"learning":[66,94,116,164],"paradigms":[67],"SSL-based":[69],"representation":[71,163],"learning,":[72],"we":[73,143],"propose":[74,144],"SLICER":[75,168],"(Symmetrical":[76],"Instance":[79],"Cluster-level":[81],"Efficient":[82],"Representations)":[83],"which":[84,155],"brings":[85],"together":[86],"best":[88],"both":[90],"paradigms.":[95],"use":[97],"symmetric":[99],"loss":[100],"between":[101],"latent":[102],"from":[104],"student":[105],"teacher":[107],"simultaneously":[110],"solve":[111],"in-stance":[112],"cluster-level":[114],"contrastive":[115],"tasks.":[117],"obtain":[119],"cluster":[120],"online":[122],"just":[124],"projecting":[125],"input":[127],"spectrogram":[128],"into":[129],"an":[130],"output":[131],"subspace":[132],"with":[133],"dimensions":[134],"equal":[135],"number":[138],"clusters.":[140],"In":[141],"addition,":[142],"novel":[146],"mel-spectrogram":[147],"augmentation":[148],"procedure":[149],"k-mix,":[150],"based":[151],"mixup":[153],"[1],":[154],"does":[156],"not":[157],"require":[158],"labels":[159],"aids":[161],"unsupervised":[162,188],"audio.":[166],"Overall,":[167],"achieves":[169],"state-of-the-art":[170],"results":[171],"LAPE":[174],"Benchmark":[175],"[2],":[176],"significantly":[177],"outperforming":[178],"all":[179],"other":[180],"prior":[181],"approaches,":[182],"some-times":[183],"pre-trained":[184],"10\u00d7":[186],"larger":[187],"than":[190],"our":[191],"Code":[193],"https:":[194],"https://github.com/Sreyan88/audio-ssl.":[195]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}