{"id":"https://openalex.org/W4403511013","doi":"https://doi.org/10.1109/lsp.2024.3483009","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","display_name":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403511013","doi":"https://doi.org/10.1109/lsp.2024.3483009"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3483009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3483009","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5043775291","display_name":"Mehmet Hamza Erol","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["KR","US"],"is_corresponding":true,"raw_author_name":"Mehmet Hamza Erol","raw_affiliation_strings":["Computer Science Department, Stanford University, Stanford, CA, USA","School of Electrical Engineering, KAIST, Korea"],"raw_orcid":"https://orcid.org/0000-0003-1909-4775","affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070707693","display_name":"Arda Senocak","orcid":"https://orcid.org/0000-0001-9141-3270"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["School of Electrical Engineering, KAIST, South Korea","School of Electrical Engineering, KAIST, Korea"],"raw_orcid":"https://orcid.org/0000-0001-9141-3270","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102441906","display_name":"Jiu Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Jiu Feng","raw_affiliation_strings":["Department of Computer Science, UT Austin, Austin, TX, USA","School of Electrical Engineering, KAIST, Korea"],"raw_orcid":"https://orcid.org/0009-0002-3626-6444","affiliations":[{"raw_affiliation_string":"Department of Computer Science, UT Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["School of Electrical Engineering, KAIST, South Korea","School of Electrical Engineering, KAIST, Korea"],"raw_orcid":"https://orcid.org/0000-0001-7741-7275","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"School of Electrical Engineering, KAIST, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043775291"],"corresponding_institution_ids":["https://openalex.org/I157485424","https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":10.597,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.99012896,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"2975","last_page":"2979"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9800000190734863,"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":0.9678000211715698,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7269871830940247},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5886378884315491},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.531527578830719},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.459597647190094},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4494284987449646},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4238243103027344},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.27476033568382263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7269871830940247},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5886378884315491},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.531527578830719},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.459597647190094},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4494284987449646},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4238243103027344},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27476033568382263},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3483009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3483009","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2981087920","https://openalex.org/W3015371781","https://openalex.org/W3094550259","https://openalex.org/W3196974791","https://openalex.org/W3207758636","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4297841853","https://openalex.org/W4312420631","https://openalex.org/W4313442864","https://openalex.org/W4319862477","https://openalex.org/W4372260217","https://openalex.org/W4372260227","https://openalex.org/W4372260310","https://openalex.org/W4385245566","https://openalex.org/W4385823047","https://openalex.org/W4403152483","https://openalex.org/W6734260513","https://openalex.org/W6750665317","https://openalex.org/W6780294235","https://openalex.org/W6784333009","https://openalex.org/W6785011006","https://openalex.org/W6788135285","https://openalex.org/W6793736971","https://openalex.org/W6797613833","https://openalex.org/W6803444062","https://openalex.org/W6810325043","https://openalex.org/W6840200333","https://openalex.org/W6841205203","https://openalex.org/W6845577938","https://openalex.org/W6859298233","https://openalex.org/W6860720708","https://openalex.org/W6860915106","https://openalex.org/W6861342692","https://openalex.org/W6861387779"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W1975359510","https://openalex.org/W1496727373","https://openalex.org/W4254699594","https://openalex.org/W2020952589","https://openalex.org/W2970176078","https://openalex.org/W1526651343","https://openalex.org/W2069094726","https://openalex.org/W2146634268","https://openalex.org/W2088690926"],"abstract_inverted_index":{"Transformers":[0,18],"have":[1,45],"rapidly":[2],"become":[3],"the":[4,76],"preferred":[5],"choice":[6],"for":[7,67,82],"audio":[8,68,83,96],"classification,":[9,84],"surpassing":[10],"methods":[11],"based":[12],"on":[13,63,94],"CNNs.":[14],"However,":[15],"Audio":[16,73],"Spectrogram":[17],"(ASTs)":[19],"exhibit":[20],"quadratic":[21,30],"scaling":[22],"due":[23],"to":[24,87,112],"self-attention.":[25],"The":[26],"removal":[27],"of":[28],"this":[29,54,57,89],"self-attention":[31,64],"cost":[32],"presents":[33],"an":[34],"appealing":[35],"direction.":[36],"Recently,":[37],"state":[38],"space":[39],"models":[40],"(SSMs),":[41],"such":[42],"as":[43],"Mamba,":[44],"demonstrated":[46],"potential":[47],"in":[48,53],"language":[49],"and":[50],"vision":[51],"tasks":[52],"regard.":[55],"In":[56],"study,":[58],"we":[59,85],"explore":[60],"whether":[61],"reliance":[62],"is":[65],"necessary":[66],"classification":[69],"tasks.":[70],"By":[71],"introducing":[72],"Mamba":[74],"(AuM),":[75],"first":[77],"self-attention-free,":[78],"purely":[79],"SSM-based":[80],"model":[81],"aim":[86],"address":[88],"question.":[90],"We":[91],"evaluate":[92],"AuM":[93],"various":[95],"datasets":[97],"-":[98,103],"comprising":[99],"six":[100],"different":[101],"benchmarks":[102],"where":[104],"it":[105],"achieves":[106],"comparable":[107],"or":[108],"better":[109],"performance":[110],"compared":[111],"well-established":[113],"AST":[114],"model.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}