{"id":"https://openalex.org/W4411444742","doi":"https://doi.org/10.1007/s10994-025-06807-z","title":"Efficient and interpretable raw audio classification with diagonal state space models","display_name":"Efficient and interpretable raw audio classification with diagonal state space models","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411444742","doi":"https://doi.org/10.1007/s10994-025-06807-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06807-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06807-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06807-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06807-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106602825","display_name":"Matthias Bittner","orcid":"https://orcid.org/0009-0004-8022-2232"},"institutions":[{"id":"https://openalex.org/I4210105054","display_name":"Christian Doppler Laboratory for Thermoelectricity","ror":"https://ror.org/01cbw5x35","country_code":"AT","type":"facility","lineage":["https://openalex.org/I129774422","https://openalex.org/I145847075","https://openalex.org/I4210105054"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Matthias Bittner","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria","institution_ids":["https://openalex.org/I4210105054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008010655","display_name":"Daniel Schn\u00f6ll","orcid":"https://orcid.org/0009-0009-5834-6526"},"institutions":[{"id":"https://openalex.org/I4210105054","display_name":"Christian Doppler Laboratory for Thermoelectricity","ror":"https://ror.org/01cbw5x35","country_code":"AT","type":"facility","lineage":["https://openalex.org/I129774422","https://openalex.org/I145847075","https://openalex.org/I4210105054"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Daniel Schn\u00f6ll","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria","institution_ids":["https://openalex.org/I4210105054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087503534","display_name":"Matthias Wess","orcid":"https://orcid.org/0000-0002-1877-4114"},"institutions":[{"id":"https://openalex.org/I4210105054","display_name":"Christian Doppler Laboratory for Thermoelectricity","ror":"https://ror.org/01cbw5x35","country_code":"AT","type":"facility","lineage":["https://openalex.org/I129774422","https://openalex.org/I145847075","https://openalex.org/I4210105054"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Matthias Wess","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria","institution_ids":["https://openalex.org/I4210105054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032163732","display_name":"Axel Jantsch","orcid":"https://orcid.org/0000-0003-2251-0004"},"institutions":[{"id":"https://openalex.org/I4210105054","display_name":"Christian Doppler Laboratory for Thermoelectricity","ror":"https://ror.org/01cbw5x35","country_code":"AT","type":"facility","lineage":["https://openalex.org/I129774422","https://openalex.org/I145847075","https://openalex.org/I4210105054"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Axel Jantsch","raw_affiliation_strings":["Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Christian Doppler Laboratory for Embedded Machine Learning, Institute for Computer Technology, TU Wien, Gu\u00dfhausstra\u00dfe 27-29, 1040, Vienna, Austria","institution_ids":["https://openalex.org/I4210105054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008010655","https://openalex.org/A5106602825"],"corresponding_institution_ids":["https://openalex.org/I4210105054"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":3.2101,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.92240076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"114","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6249632239341736},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.5856941938400269},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.5483412146568298},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5251145958900452},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5224398970603943},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4965711236000061},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.4708881974220276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37856340408325195},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3614598512649536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2540917694568634},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1752205491065979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6249632239341736},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.5856941938400269},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.5483412146568298},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5251145958900452},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5224398970603943},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4965711236000061},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4708881974220276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37856340408325195},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3614598512649536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2540917694568634},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1752205491065979},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06807-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06807-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06807-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06807-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06807-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06807-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322839","display_name":"Technische Universit\u00e4t Wien","ror":"https://ror.org/04d836q62"},{"id":"https://openalex.org/F4320323591","display_name":"Christian Doppler Forschungsgesellschaft","ror":"https://ror.org/00mv8h305"},{"id":"https://openalex.org/F4320327593","display_name":"Bundesministerium f\u00fcr Digitalisierung und Wirtschaftsstandort","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411444742.pdf","grobid_xml":"https://content.openalex.org/works/W4411444742.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W581347801","https://openalex.org/W2064675550","https://openalex.org/W2107878631","https://openalex.org/W2128084896","https://openalex.org/W2313162948","https://openalex.org/W2735048321","https://openalex.org/W2964199361","https://openalex.org/W3143174503","https://openalex.org/W3154934206","https://openalex.org/W3198591403","https://openalex.org/W3209374680","https://openalex.org/W4221145950","https://openalex.org/W4254816979","https://openalex.org/W4283461773","https://openalex.org/W4283658602","https://openalex.org/W4313009049","https://openalex.org/W4313496578","https://openalex.org/W4322707137","https://openalex.org/W4324312887","https://openalex.org/W4387075182","https://openalex.org/W4387244556","https://openalex.org/W4389326242","https://openalex.org/W4394866661","https://openalex.org/W4401568792","https://openalex.org/W4402641424","https://openalex.org/W6729053843","https://openalex.org/W6739901393","https://openalex.org/W6785783668","https://openalex.org/W6841205203","https://openalex.org/W6843735039"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W4310746709","https://openalex.org/W4386075645","https://openalex.org/W4385574037","https://openalex.org/W4306309518","https://openalex.org/W4286967710"],"abstract_inverted_index":{"Abstract":[0],"State":[1],"Space":[2],"Models":[3],"have":[4],"achieved":[5],"good":[6],"performance":[7],"on":[8,48,97,134],"long":[9],"sequence":[10],"modeling":[11],"tasks":[12],"such":[13],"as":[14],"raw":[15],"audio":[16],"classification.":[17],"Their":[18],"definition":[19],"in":[20,115,170,174,181],"continuous":[21],"time":[22,145],"allows":[23,80],"for":[24],"discretization":[25],"and":[26,86,92,150,177],"operation":[27],"of":[28,56,90],"the":[29,45,67,98,138,151],"network":[30],"at":[31,111,125],"different":[32],"sampling":[33],"rates.":[34],"However,":[35],"this":[36],"property":[37],"has":[38],"not":[39],"yet":[40],"been":[41],"utilized":[42],"to":[43,65,82,94,117],"decrease":[44],"computational":[46],"demand":[47],"a":[49,54,61,118,164],"per-layer":[50],"basis.":[51],"We":[52],"propose":[53],"family":[55],"hardware-friendly":[57],"S-Edge":[58,105],"models":[59,106],"with":[60,122,146,154],"layer-wise":[62],"downsampling":[63],"approach":[64],"adjust":[66],"temporal":[68],"resolution":[69],"between":[70],"individual":[71],"layers.":[72],"Applying":[73],"existing":[74],"methods":[75],"from":[76,108],"linear":[77],"control":[78],"theory":[79],"us":[81],"analyze":[83],"state/memory":[84],"dynamics":[85],"provides":[87],"an":[88,135],"understanding":[89],"how":[91],"where":[93],"downsample.":[95],"Evaluated":[96],"Google":[99],"Speech":[100],"Command":[101],"dataset,":[102],"our":[103,130],"autoregressive/causal":[104],"range":[107],"8\u2013141k":[109],"parameters":[110,124],"90\u201395%":[112],"test":[113,127,148,156],"accuracy":[114],"comparison":[116],"causal":[119],"S5":[120],"model":[121,140,153,171],"208k":[123],"95.8%":[126],"accuracy.":[128,182],"Using":[129],"C++17":[131],"header-only":[132],"implementation":[133],"ARM":[136],"Cortex-M4F":[137],"largest":[139],"requires":[141,158],"103":[142],"sec.":[143,160],"inference":[144,175],"95.19%":[147],"accuracy,":[149,157],"smallest":[152],"88.01%":[155],"0.29":[159],"Our":[161],"solutions":[162],"cover":[163],"design":[165],"space":[166],"that":[167],"spans":[168],"17x":[169],"size,":[172],"358x":[173],"latency,":[176],"7.18":[178],"percentage":[179],"points":[180]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}