{"id":"https://openalex.org/W4415433180","doi":"https://doi.org/10.21437/interspeech.2025-1612","title":"\u201cKAN you hear me?\u201d Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding","display_name":"\u201cKAN you hear me?\u201d Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433180","doi":"https://doi.org/10.21437/interspeech.2025-1612"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1612","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1612","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":"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/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057352420","display_name":"Eliana Pastor","orcid":"https://orcid.org/0000-0002-3664-4137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eliana Pastor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001695309","display_name":"Elena Baralis","orcid":"https://orcid.org/0000-0001-9231-467X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Baralis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93591995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4123","last_page":"4127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9621999859809875,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9621999859809875,"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/T10028","display_name":"Topic Modeling","score":0.9467999935150146,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9298999905586243,"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/spoken-language","display_name":"Spoken language","score":0.6642000079154968},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5166000127792358},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4781999886035919},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4740999937057495},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3580000102519989},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489999890327454},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5166000127792358},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36739999055862427},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34769999980926514},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2667999863624573}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1612","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1612","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:iris.unipa.it:10447/694131","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/694131","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Kolmogorov-Arnold":[0],"Networks":[1],"(KANs)":[2],"have":[3],"recently":[4],"emerged":[5],"as":[6],"a":[7,61],"promising":[8],"alternative":[9],"to":[10,17,71,119],"traditional":[11],"neural":[12],"architectures,":[13],"yet":[14],"their":[15],"application":[16],"speech":[18],"processing":[19],"remains":[20],"under":[21],"explored.":[22],"This":[23],"work":[24],"presents":[25],"the":[26,53,92,123],"first":[27],"investigation":[28],"of":[29,115,122],"KANs":[30],"for":[31],"Spoken":[32],"Language":[33],"Understanding":[34],"(SLU)":[35],"tasks.":[36],"We":[37],"experiment":[38],"with":[39,80],"2D-CNN":[40],"models":[41,73],"on":[42,76,113],"two":[43,65],"datasets,":[44],"integrating":[45],"KAN":[46,62,87,109],"layers":[47,88,112],"in":[48,100],"five":[49,77],"different":[50],"configurations":[51],"within":[52],"dense":[54],"block.":[55],"The":[56],"best-performing":[57],"setup,":[58],"which":[59],"places":[60],"layer":[63],"between":[64],"linear":[66,93,111],"layers,":[67,94],"is":[68],"directly":[69],"applied":[70],"transformer-based":[72],"and":[74,110],"evaluated":[75],"SLU":[78],"datasets":[79],"increasing":[81],"complexity.":[82],"Our":[83],"results":[84],"show":[85],"that":[86],"can":[89],"effectively":[90],"replace":[91],"achieving":[95],"comparable":[96],"or":[97],"superior":[98],"performance":[99],"most":[101],"cases.":[102],"Finally,":[103],"we":[104],"provide":[105],"insights":[106],"into":[107],"how":[108],"top":[114],"transformers":[116],"differently":[117],"attend":[118],"input":[120],"regions":[121],"raw":[124],"waveforms.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}