{"id":"https://openalex.org/W4402111418","doi":"https://doi.org/10.21437/interspeech.2024-1274","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","display_name":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111418","doi":"https://doi.org/10.21437/interspeech.2024-1274"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1274","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/ws/files/770969585/yadav24_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000317921","display_name":"Sarthak Yadav","orcid":"https://orcid.org/0000-0002-1979-9460"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sarthak Yadav","raw_affiliation_strings":["Aalborg University, The Technical Faculty of IT and Design, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Aalborg University, The Technical Faculty of IT and Design, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University, The Technical Faculty of IT and Design, DK","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I891191580"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"552","last_page":"556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9926999807357788,"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":0.9865000247955322,"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":0.852530837059021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7167683839797974},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5927667617797852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5261837244033813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48945868015289307},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4338718354701996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4000309109687805},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09444093704223633}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.852530837059021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167683839797974},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5927667617797852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5261837244033813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48945868015289307},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4338718354701996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4000309109687805},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09444093704223633},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-1274","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/335de060-a3b7-4de3-b791-d8f7c318ce88","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/335de060-a3b7-4de3-b791-d8f7c318ce88","pdf_url":"https://vbn.aau.dk/ws/files/770969585/yadav24_interspeech.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yadav, S & Tan, Z-H 2024, Audio Mamba : Selective State Spaces for Self-Supervised Audio Representations. in Interspeech 2024. International Speech Communication Association, Proceedings of the International Conference on Spoken Language Processing, pp. 552-556, INTERSPEECH 2024, Kos Island, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1274","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/335de060-a3b7-4de3-b791-d8f7c318ce88","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/335de060-a3b7-4de3-b791-d8f7c318ce88","pdf_url":"https://vbn.aau.dk/ws/files/770969585/yadav24_interspeech.pdf","source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yadav, S & Tan, Z-H 2024, Audio Mamba : Selective State Spaces for Self-Supervised Audio Representations. in Interspeech 2024. International Speech Communication Association, Proceedings of the International Conference on Spoken Language Processing, pp. 552-556, INTERSPEECH 2024, Kos Island, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1274","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111418.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W2942893872","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Despite":[0],"its":[1,20],"widespread":[2],"adoption":[3],"as":[4],"the":[5,9,85,90],"prominent":[6],"neural":[7],"architecture,":[8],"Transformer":[10],"has":[11],"spurred":[12],"several":[13],"independent":[14],"lines":[15],"of":[16],"work":[17,53],"to":[18,49],"address":[19],"limitations.":[21],"One":[22],"such":[23],"approach":[24],"is":[25,47],"selective":[26,58],"state":[27,59],"space":[28,60],"models,":[29,87],"which":[30],"have":[31],"demonstrated":[32],"promising":[33],"results":[34,75],"for":[35,41,62],"language":[36],"modelling.":[37],"However,":[38],"their":[39],"feasibility":[40],"learning":[42,63],"self-supervised,":[43],"general-purpose":[44,64],"audio":[45,65,79,97],"representations":[46,66],"yet":[48],"be":[50],"investigated.":[51],"This":[52],"proposes":[54],"Audio":[55],"Mamba,":[56],"a":[57,103],"model":[61,116],"from":[67],"randomly":[68],"masked":[69],"spectrogram":[70,98],"patches":[71],"through":[72],"self-supervision.":[73],"Empirical":[74],"on":[76,89],"ten":[77],"diverse":[78],"recognition":[80],"downstream":[81],"tasks":[82],"show":[83],"that":[84],"proposed":[86],"pretrained":[88],"AudioSet":[91],"dataset,":[92],"consistently":[93],"outperform":[94],"comparable":[95],"self-supervised":[96],"transformer":[99],"(SSAST)":[100],"baselines":[101],"by":[102],"considerable":[104],"margin":[105],"and":[106,115],"demonstrate":[107],"better":[108],"performance":[109],"in":[110],"dataset":[111],"size,":[112],"sequence":[113],"length":[114],"size":[117],"comparisons.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}