{"id":"https://openalex.org/W4406461620","doi":"https://doi.org/10.1109/slt61566.2024.10832304","title":"SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model","display_name":"SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461620","doi":"https://doi.org/10.1109/slt61566.2024.10832304"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5110962863","display_name":"Siavash Shams","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siavash Shams","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087242188","display_name":"Sukru Samet Dindar","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sukru Samet Dindar","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109460203","display_name":"Xilin Jiang","orcid":"https://orcid.org/0009-0000-9373-0851"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xilin Jiang","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Columbia University,Department of Electrical Engineering,USA"],"affiliations":[{"raw_affiliation_string":"Columbia University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110962863"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":7.947,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.98335718,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1053","last_page":"1059"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9962000250816345,"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":0.7128613591194153},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6042422652244568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43336498737335205},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42259329557418823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3343058228492737}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128613591194153},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6042422652244568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43336498737335205},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42259329557418823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3343058228492737},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338440","display_name":"HORIZON EUROPE Health","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2105934661","https://openalex.org/W2146334809","https://openalex.org/W2593116425","https://openalex.org/W2726515241","https://openalex.org/W2797583228","https://openalex.org/W2842511635","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W3036601975","https://openalex.org/W3196974791","https://openalex.org/W3206996142","https://openalex.org/W3209059054","https://openalex.org/W3209374680","https://openalex.org/W3212492847","https://openalex.org/W4281492411","https://openalex.org/W4293363567","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W4389326242","https://openalex.org/W4390784781","https://openalex.org/W4391013663","https://openalex.org/W4391506277","https://openalex.org/W4393300076","https://openalex.org/W4399939359","https://openalex.org/W4403067091","https://openalex.org/W4403152483","https://openalex.org/W4403842425","https://openalex.org/W4404586723","https://openalex.org/W6750665317","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6802912272","https://openalex.org/W6803444062","https://openalex.org/W6859298233","https://openalex.org/W6860809164","https://openalex.org/W6860915106","https://openalex.org/W6861387779","https://openalex.org/W6862687296"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Transformers":[0],"have":[1,44],"revolutionized":[2],"deep":[3],"learning":[4],"across":[5],"various":[6,132],"tasks,":[7],"including":[8],"audio":[9,70,89,100,122,136,212],"representation":[10,90],"learning,":[11],"due":[12],"to":[13,97,119],"their":[14,35],"powerful":[15],"modeling":[16],"capabilities.":[17],"However,":[18],"they":[19],"often":[20],"suffer":[21],"from":[22,124],"quadratic":[23],"complexity":[24],"in":[25,69,157,166],"both":[26,111],"GPU":[27],"memory":[28],"usage":[29],"and":[30,85,113,142,170],"computational":[31],"inference":[32,168],"time,":[33],"affecting":[34],"efficiency.":[36],"Recently,":[37],"state":[38],"space":[39],"models":[40,68],"(SSMs)":[41],"like":[42],"Mamba":[43,79,96],"emerged":[45],"as":[46,135],"a":[47,51,105,204,208],"promising":[48],"alternative,":[49],"offering":[50],"more":[52,172],"efficient":[53],"approach":[54],"by":[55],"avoiding":[56],"these":[57,60],"complexities.":[58],"Given":[59],"advantages,":[61],"we":[62,75],"explore":[63],"the":[64,81,94,117,151,177,196],"potential":[65],"of":[66,186,198,211],"SSM-based":[67,86],"tasks.":[71,159],"In":[72],"this":[73],"paper,":[74],"introduce":[76],"Self-Supervised":[77,152],"Audio":[78,153],"(SSAMBA),":[80],"first":[82],"self-supervised,":[83],"attention-free,":[84],"model":[87,118,179],"for":[88,176,207],"learning.":[91],"SSAMBA":[92,130,149,161],"leverages":[93],"bidirectional":[95],"capture":[98],"complex":[99],"patterns":[101],"effectively.":[102],"We":[103,128],"incorporate":[104],"self-supervised":[106],"pretraining":[107],"framework":[108],"that":[109,148],"optimizes":[110],"discriminative":[112],"generative":[114],"objectives,":[115],"enabling":[116],"learn":[120],"robust":[121],"representations":[123],"large-scale,":[125],"unlabeled":[126],"datasets.":[127],"evaluated":[129],"on":[131],"tasks":[133],"such":[134],"classification,":[137],"keyword":[138],"spotting,":[139],"speaker":[140],"identification,":[141],"emotion":[143],"recognition.":[144],"Our":[145],"results":[146],"demonstrate":[147],"outperforms":[150],"Spectrogram":[154],"Transformer":[155],"(SSAST)":[156],"most":[158],"Notably,":[160],"is":[162],"approximately":[163],"92.7%":[164],"faster":[165],"batch":[167],"speed":[169],"95.4%":[171],"memory-efficient":[173],"than":[174],"SSAST":[175],"tiny":[178],"size":[180,185],"with":[181,192],"an":[182],"input":[183],"token":[184],"22k.":[187],"These":[188],"efficiency":[189],"gains,":[190],"combined":[191],"superior":[193],"performance,":[194],"underscore":[195],"effectiveness":[197],"SSAMBA\u2019s":[199],"architectural":[200],"innovation,":[201],"making":[202],"it":[203],"compelling":[205],"choice":[206],"wide":[209],"range":[210],"processing":[213],"applications.":[214],"Code":[215],"at":[216],"https://github.com/SiavashShams/ssamba.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}