{"id":"https://openalex.org/W4317425714","doi":"https://doi.org/10.1186/s13636-023-00271-0","title":"Trainable windows for SincNet architecture","display_name":"Trainable windows for SincNet architecture","publication_year":2023,"publication_date":"2023-01-19","ids":{"openalex":"https://openalex.org/W4317425714","doi":"https://doi.org/10.1186/s13636-023-00271-0"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00271-0","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13636-023-00271-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00271-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00271-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055771008","display_name":"H C Prashanth","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prashanth H C","raw_affiliation_strings":["International Institute of Information Technology Bangalore, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061397479","display_name":"Madhav Rao","orcid":"https://orcid.org/0000-0003-2278-9148"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Madhav Rao","raw_affiliation_strings":["International Institute of Information Technology Bangalore, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0003-2278-9148","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024759703","display_name":"Dhanya Eledath","orcid":null},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhanya Eledath","raw_affiliation_strings":["International Institute of Information Technology Bangalore, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036811576","display_name":"V. Ramasubramanian","orcid":"https://orcid.org/0000-0002-0676-9174"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramasubramanian V","raw_affiliation_strings":["International Institute of Information Technology Bangalore, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore, Bangalore, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061397479"],"corresponding_institution_ids":["https://openalex.org/I181514455"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.7856,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76014146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"2023","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9980999827384949,"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/window-function","display_name":"Window function","score":0.762130618095398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256269454956055},{"id":"https://openalex.org/keywords/spectral-leakage","display_name":"Spectral leakage","score":0.599953293800354},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.5519301295280457},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.526621401309967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5028092861175537},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4767923355102539},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46251335740089417},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43899163603782654},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4258565902709961},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38349857926368713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.336877703666687},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3255993127822876},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.14841610193252563},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.11307185888290405},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1112821102142334},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10122150182723999}],"concepts":[{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.762130618095398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256269454956055},{"id":"https://openalex.org/C113407356","wikidata":"https://www.wikidata.org/wiki/Q1431214","display_name":"Spectral leakage","level":3,"score":0.599953293800354},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.5519301295280457},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.526621401309967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5028092861175537},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4767923355102539},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46251335740089417},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43899163603782654},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4258565902709961},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38349857926368713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.336877703666687},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3255993127822876},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.14841610193252563},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.11307185888290405},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1112821102142334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10122150182723999},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-023-00271-0","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13636-023-00271-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00271-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d744ed482f6c489189e0989edb5322c8","is_oa":true,"landing_page_url":"https://doaj.org/article/d744ed482f6c489189e0989edb5322c8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-9 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00271-0","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1186/s13636-023-00271-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00271-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4317425714.pdf","grobid_xml":"https://content.openalex.org/works/W4317425714.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2962901777","https://openalex.org/W2964052309","https://openalex.org/W3007948068","https://openalex.org/W3015287265","https://openalex.org/W3094788075","https://openalex.org/W3114586009","https://openalex.org/W3129570578","https://openalex.org/W3203902498","https://openalex.org/W4206656904"],"related_works":["https://openalex.org/W2972825155","https://openalex.org/W2891300059","https://openalex.org/W2393141619","https://openalex.org/W2944231375","https://openalex.org/W3143386729","https://openalex.org/W2390655494","https://openalex.org/W3128096547","https://openalex.org/W2156795875","https://openalex.org/W1557270426","https://openalex.org/W2243740808"],"abstract_inverted_index":{"Abstract":[0],"SincNet":[1,18,34,54,85,143,170],"architecture":[2,86],"has":[3],"shown":[4],"significant":[5],"benefits":[6],"over":[7,164],"traditional":[8],"Convolutional":[9],"Neural":[10],"Networks":[11],"(CNN),":[12],"especially":[13],"for":[14,132],"speaker":[15,88],"recognition":[16,89],"applications.":[17],"comprises":[19],"parameterized":[20],"Sinc":[21],"functions":[22,83,102,149],"as":[23,66],"filters":[24],"in":[25,37,53,96,122,137,157],"the":[26,44,47,67,110,115,118,125,133,138,142,158],"first":[27,139],"layer":[28,140],"followed":[29],"by":[30],"convolutional":[31],"layers.":[32],"Although":[33],"is":[35,55],"compact":[36],"nature":[38],"and":[39,61,129,147,155],"offers":[40],"top-level":[41],"understanding":[42],"of":[43,49,79,117,124,141,153],"features":[45],"extracted,":[46],"effect":[48,116],"window":[50,101,166],"function":[51,121],"used":[52,65],"not":[56],"thoroughly":[57],"addressed":[58],"yet.":[59],"Hamming":[60,165],"Hann":[62],"are":[63],"popularly":[64],"default":[68],"time-localized":[69,119],"windows":[70],"to":[71,108],"reduce":[72],"spectral":[73,130],"leakage.":[74],"Hence,":[75],"a":[76],"comprehensive":[77],"investigation":[78],"28":[80],"different":[81],"windowing":[82,120],"on":[84,169],"towards":[87],"task":[90],"using":[91],"TIMIT":[92],"dataset":[93],"was":[94],"performed":[95],"this":[97],"work.":[98],"Additionally,":[99],"\u201ctrainable\u201d":[100],"were":[103],"configured":[104],"with":[105],"tunable":[106],"parameters":[107],"characterize":[109],"performance.":[111],"The":[112],"paper":[113],"benchmarks":[114],"terms":[123],"bandwidth,":[126],"side-lobe":[127],"suppression,":[128],"leakage":[131],"filter":[134],"banks":[135],"employed":[136,168],"architecture.":[144,171],"Trainable":[145],"Gaussian":[146],"Cosine-Sum":[148],"exhibited":[150],"relative":[151],"improvement":[152],"41.46%":[154],"82.11%":[156],"sentence":[159],"level":[160],"classification":[161],"error":[162],"rate":[163],"when":[167]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}