{"id":"https://openalex.org/W4415433500","doi":"https://doi.org/10.21437/interspeech.2025-896","title":"From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology","display_name":"From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433500","doi":"https://doi.org/10.21437/interspeech.2025-896"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-896","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-896","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100369534","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0001-9543-1767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100598749","display_name":"Yuchen Hu","orcid":"https://orcid.org/0009-0002-6789-2093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchen Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418563","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3498-2527"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","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":"middle","author":{"id":"https://openalex.org/A5045623329","display_name":"Songting Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songting Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","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":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5153","last_page":"5157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.899399995803833,"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/T10860","display_name":"Speech and Audio Processing","score":0.899399995803833,"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/pesq","display_name":"PESQ","score":0.8971999883651733},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.8564000129699707},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7501000165939331},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5874999761581421},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4984999895095825},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4790000021457672},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4781000018119812},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4571000039577484}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8971999883651733},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8564000129699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537999749183655},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7501000165939331},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909000098705292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4790000021457672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.38370001316070557},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.37619999051094055},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36489999294281006},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2799000144004822}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-896","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-896","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:10447/694126","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/694126","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)-based":[3],"speech":[4],"enhancement":[5],"(SE)":[6],"usually":[7],"uses":[8],"conventional":[9],"activation":[10],"functions,":[11],"which":[12],"lack":[13],"the":[14,58,68,73,116],"expressiveness":[15,36],"to":[16,46,84,93,111],"capture":[17],"complex":[18,41],"multiscale":[19],"structures":[20],"needed":[21],"for":[22,123,139],"high-fidelity":[23],"SE.":[24,140],"Group-Rational":[25],"KAN":[26],"(GR-KAN),":[27],"a":[28,104,136],"variant":[29],"of":[30,120],"Kolmogorov-Arnold":[31],"Networks":[32],"(KAN),":[33],"retains":[34],"KAN's":[35],"while":[37,88],"improving":[38,89],"scalability":[39,99],"on":[40,77,103],"tasks.":[42],"We":[43,114],"adapt":[44],"GR-KAN":[45,55,81,134],"existing":[47],"DNN-based":[48],"SE":[49],"by":[50,91],"replacing":[51],"dense":[52],"layers":[53,56,71],"with":[54],"in":[57,72,126],"time-frequency":[59],"(T-F)":[60],"domain":[61],"MP-SENet":[62],"and":[63,129],"adapting":[64],"GR-KAN's":[65],"activations":[66],"into":[67],"1D":[69],"CNN":[70],"time-domain":[74],"Demucs.":[75],"Results":[76],"Voicebank-DEMAND":[78],"show":[79],"that":[80],"requires":[82],"up":[83,92],"4\u00d7":[85],"fewer":[86],"parameters":[87],"PESQ":[90],"0.1.":[94],"In":[95],"contrast,":[96],"KAN,":[97],"facing":[98],"issues,":[100],"outperforms":[101],"MLP":[102],"small-scale":[105],"signal":[106],"modeling":[107],"task":[108],"but":[109],"fails":[110],"improve":[112],"MP-SENet.":[113],"demonstrate":[115],"first":[117],"successful":[118],"use":[119],"KAN-based":[121],"methods":[122],"consistent":[124],"improvement":[125],"both":[127],"time-":[128],"SoTA":[130],"TF-domain":[131],"SE,":[132],"establishing":[133],"as":[135],"promising":[137],"alternative":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}