{"id":"https://openalex.org/W4415433715","doi":"https://doi.org/10.21437/interspeech.2025-426","title":"AxLSTMs: learning self-supervised audio representations with xLSTMs","display_name":"AxLSTMs: learning self-supervised audio representations with xLSTMs","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433715","doi":"https://doi.org/10.21437/interspeech.2025-426"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/802482218/Version_of_Record.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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sarthak Yadav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085953846","display_name":"Sergios Theodoridis","orcid":"https://orcid.org/0000-0001-5040-161X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergios Theodoridis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3524","last_page":"3528"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9922000169754028,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8525999784469604},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6550999879837036},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43869999051094055},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41589999198913574},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41110000014305115},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8525999784469604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6588000059127808},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6550999879837036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2840999960899353},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-426","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/48f30ec1-cc43-4395-b737-7e5b3ba768fa","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/48f30ec1-cc43-4395-b737-7e5b3ba768fa","pdf_url":"https://vbn.aau.dk/ws/files/802482218/Version_of_Record.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, Theodoridis, S & Tan, Z H 2025, AxLSTMs : learning self-supervised audio representations with xLSTMs. in Interspeech 2025. The International Speech Communication Association (ISCA), INTERSPEECH , pp. 3524-3528, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-426","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/48f30ec1-cc43-4395-b737-7e5b3ba768fa","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/48f30ec1-cc43-4395-b737-7e5b3ba768fa","pdf_url":"https://vbn.aau.dk/ws/files/802482218/Version_of_Record.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, Theodoridis, S & Tan, Z H 2025, AxLSTMs : learning self-supervised audio representations with xLSTMs. in Interspeech 2025. The International Speech Communication Association (ISCA), INTERSPEECH , pp. 3524-3528, Interspeech 2025, Rotterdam, Netherlands, 17/08/2025. https://doi.org/10.21437/Interspeech.2025-426","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433715.pdf","grobid_xml":"https://content.openalex.org/works/W4415433715.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"the":[1,6,32,41,53,89,92],"transformer":[2,101],"has":[3,63],"emerged":[4,16],"as":[5],"eminent":[7],"neural":[8,22],"architecture,":[9,38],"several":[10],"independent":[11],"lines":[12],"of":[13,28,114],"research":[14],"have":[15,24,47],"to":[17,52,106,122],"address":[18],"its":[19],"limitations.":[20],"Recurrent":[21],"approaches":[23],"observed":[25],"a":[26,84,112],"lot":[27],"renewed":[29],"interest,":[30],"including":[31],"extended":[33],"long":[34],"short-term":[35],"memory":[36],"(xLSTM)":[37],"which":[39],"reinvigorates":[40],"original":[42],"LSTM.":[43],"However,":[44],"while":[45,119],"xLSTMs":[46],"shown":[48],"competitive":[49],"performance":[50,110],"compared":[51],"transformer,":[54],"their":[55],"viability":[56],"for":[57,75],"learning":[58,76],"self-supervised":[59,85,98],"general-purpose":[60],"audio":[61,77,99],"representations":[62,78],"not":[64],"been":[65],"evaluated.":[66],"This":[67],"work":[68],"proposes":[69],"Audio":[70],"xLSTM":[71],"(AxLSTM),":[72],"an":[73],"approach":[74],"from":[79],"masked":[80],"spectrogram":[81,100],"patches":[82],"in":[83,108],"setting.":[86],"Pretrained":[87],"on":[88],"AudioSet":[90],"dataset,":[91],"proposed":[93],"AxLSTM":[94],"models":[95],"outperform":[96],"comparable":[97],"(SSAST)":[102],"baselines":[103],"by":[104],"up":[105,121],"25%":[107],"relative":[109],"across":[111],"set":[113],"ten":[115],"diverse":[116],"downstream":[117],"tasks":[118],"having":[120],"45%":[123],"fewer":[124],"parameters.":[125]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}