{"id":"https://openalex.org/W4392903373","doi":"https://doi.org/10.1109/icassp48485.2024.10446318","title":"Filamentary Convolution for Spoken Language Identification: A Brain-Inspired Approach","display_name":"Filamentary Convolution for Spoken Language Identification: A Brain-Inspired Approach","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903373","doi":"https://doi.org/10.1109/icassp48485.2024.10446318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101684487","display_name":"Boyuan Zhang","orcid":"https://orcid.org/0000-0001-7286-931X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyuan Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089933678","display_name":"Shuyuan Zhu","orcid":"https://orcid.org/0000-0003-4450-3868"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyuan Zhu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101014790","display_name":"Tong Xie","orcid":"https://orcid.org/0000-0003-2999-622X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tong Xie","raw_affiliation_strings":["Nanyang Technological University,Singapore","Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319169","display_name":"Xibang Yang","orcid":"https://orcid.org/0009-0006-4310-7424"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xibang Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375505","display_name":"Yahui Liu","orcid":"https://orcid.org/0000-0002-6889-4763"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahui Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077470082","display_name":"Bing Zeng","orcid":"https://orcid.org/0000-0002-4491-7967"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Zeng","raw_affiliation_strings":["University of Electronic Science and Technology of China,Chengdu,China","University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9926","last_page":"9930"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7807891964912415},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6535964608192444},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6213822960853577},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.535297691822052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296167135238647},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5176313519477844},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4756079316139221},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.46852418780326843},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44961825013160706},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4448801279067993},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4289821982383728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41829726099967957},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.41604483127593994},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3918435573577881},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3455957770347595},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.333354651927948},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.09966170787811279},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09826505184173584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807891964912415},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6535964608192444},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6213822960853577},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.535297691822052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296167135238647},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5176313519477844},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4756079316139221},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46852418780326843},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44961825013160706},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4448801279067993},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4289821982383728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41829726099967957},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.41604483127593994},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3918435573577881},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3455957770347595},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.333354651927948},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.09966170787811279},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09826505184173584},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W178568469","https://openalex.org/W1983072039","https://openalex.org/W2017347948","https://openalex.org/W2078169166","https://openalex.org/W2090816896","https://openalex.org/W2371039490","https://openalex.org/W2512537248","https://openalex.org/W2766570941","https://openalex.org/W2940073716","https://openalex.org/W2963604492","https://openalex.org/W2972433488","https://openalex.org/W2999579474","https://openalex.org/W3007260291","https://openalex.org/W3150131481","https://openalex.org/W3193706553","https://openalex.org/W4205550605","https://openalex.org/W4221158519","https://openalex.org/W4319779707","https://openalex.org/W4375868770","https://openalex.org/W4380591212","https://openalex.org/W6753232330"],"related_works":["https://openalex.org/W2008311543","https://openalex.org/W2802845977","https://openalex.org/W2078793534","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W3008689640","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Spoken":[0],"language":[1],"identification":[2],"(SLI)":[3],"by":[4,190],"human":[5],"beings":[6],"relies":[7],"on":[8,182],"the":[9,19,24,51,62,96,162,193],"hierarchical":[10,166],"understanding":[11],"of":[12,53,64],"one":[13],"or":[14],"a":[15,32,47,89,123,127,150,183,200],"few":[16],"words":[17],"within":[18,23,111],"voice":[20],"signal,":[21],"encapsulated":[22],"corresponding":[25],"time":[26,75],"windows.":[27],"Concurrently,":[28],"frequency-domain":[29],"features":[30,141],"play":[31],"crucial":[33],"role":[34],"in":[35,50,67,79,203],"enhancing":[36],"identification.":[37],"The":[38,139],"short-time":[39],"Fourier":[40],"transform":[41],"(STFT)":[42],"has":[43],"conventionally":[44],"served":[45],"as":[46],"pivotal":[48],"component":[49,71],"forefront":[52],"most":[54],"SLI":[55],"systems,":[56],"including":[57],"deep-learning":[58],"networks":[59],"(DLNs).":[60],"Nevertheless,":[61],"use":[63],"rectangle-shaped":[65,98],"masks":[66],"STFT":[68],"introduces":[69],"spectral":[70],"mixing":[72],"across":[73],"different":[74],"windows,":[76],"potentially":[77],"resulting":[78],"an":[80,119,171],"aliasing":[81],"effect.":[82],"To":[83],"address":[84],"this":[85],"limitation,":[86],"we":[87,117],"propose":[88],"novel":[90,184],"filamentary":[91,115,144,163],"convolution":[92,136,164],"framework":[93,101],"to":[94],"replace":[95],"conventional":[97],"convolutions.":[99],"This":[100],"not":[102],"only":[103],"reduces":[104],"complexity":[105],"but":[106],"also":[107],"enhances":[108],"feature":[109],"learning":[110],"each":[112],"frame.":[113],"Leveraging":[114],"convolution,":[116],"formulate":[118],"encoding":[120,172],"module":[121,132],"with":[122],"non-overlapping":[124],"strategy":[125],"and":[126,176,192],"multi-level":[128],"information":[129],"extraction":[130],"(MIE)":[131],"featuring":[133],"unbalanced":[134],"dual-route":[135],"(UDRC)":[137],"blocks.":[138],"frequency":[140],"learned":[142],"from":[143],"convolutions":[145],"are":[146],"seamlessly":[147],"integrated":[148],"through":[149],"long-short":[151],"term":[152],"memory":[153],"(LSTM)":[154],"structure.":[155],"In":[156],"summary,":[157],"our":[158,197],"decision-making":[159],"process":[160],"employs":[161],"kernel-based":[165],"neural":[167],"network":[168],"(FCK-NN),":[169],"comprising":[170],"module,":[173,175],"MIE":[174],"LSTM":[177],"module.":[178],"We":[179],"conduct":[180],"experiments":[181],"dataset":[185],"encompassing":[186],"44":[187],"languages,":[188],"curated":[189],"ourselves,":[191],"results":[194],"validate":[195],"that":[196],"FCK-NN":[198],"yields":[199],"significant":[201],"improvement":[202],"performance.":[204]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}