{"id":"https://openalex.org/W4308521110","doi":"https://doi.org/10.21437/iberspeech.2022-30","title":"The role of window length and shift in complex-domain DNN-based speech enhancement","display_name":"The role of window length and shift in complex-domain DNN-based speech enhancement","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W4308521110","doi":"https://doi.org/10.21437/iberspeech.2022-30"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2022-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digibug.ugr.es/bitstream/10481/80607/1/template.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025663954","display_name":"Celia Garc\u00eda-Ruiz","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Celia Garc\u00eda-Ruiz","raw_affiliation_strings":["Dpt. Signal Theory, Telematics and Communications, University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpt. Signal Theory, Telematics and Communications, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024291487","display_name":"\u00c1ngel M. G\u00f3mez","orcid":"https://orcid.org/0000-0002-9995-3068"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Angel M. Gomez","raw_affiliation_strings":["Dpt. Signal Theory, Telematics and Communications, University of Granada, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dpt. Signal Theory, Telematics and Communications, University of Granada, Spain","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064609638","display_name":"Juan M. Mart\u00edn-Do\u00f1as","orcid":"https://orcid.org/0000-0003-4874-0166"},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan M. Mart\u00edn-Do\u00f1as","raw_affiliation_strings":["Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, 20009 Donostia-San Sebasti\u00e1n (Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundaci\u00f3n Vicomtech, Basque Research and Technology Alliance (BRTA), Mikeletegi 57, 20009 Donostia-San Sebasti\u00e1n (Spain","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12513547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"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":0.7489127516746521},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6853743195533752},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6540150046348572},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6388884782791138},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5892665386199951},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4966168999671936},{"id":"https://openalex.org/keywords/attenuation","display_name":"Attenuation","score":0.4828275144100189},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4791766405105591},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.44737258553504944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43595778942108154},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4343017339706421},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4162684381008148},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4056650996208191},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.3905780017375946},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21292132139205933},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.15778616070747375},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15386053919792175},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1003294587135315}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489127516746521},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6853743195533752},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6540150046348572},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6388884782791138},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5892665386199951},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4966168999671936},{"id":"https://openalex.org/C184652730","wikidata":"https://www.wikidata.org/wiki/Q2357982","display_name":"Attenuation","level":2,"score":0.4828275144100189},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4791766405105591},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.44737258553504944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43595778942108154},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4343017339706421},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4162684381008148},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4056650996208191},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.3905780017375946},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21292132139205933},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.15778616070747375},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15386053919792175},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1003294587135315},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/iberspeech.2022-30","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-30","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:digibug.ugr.es:10481/80607","is_oa":true,"landing_page_url":"https://hdl.handle.net/10481/80607","pdf_url":"https://digibug.ugr.es/bitstream/10481/80607/1/template.pdf","source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:digibug.ugr.es:10481/80607","is_oa":true,"landing_page_url":"https://hdl.handle.net/10481/80607","pdf_url":"https://digibug.ugr.es/bitstream/10481/80607/1/template.pdf","source":{"id":"https://openalex.org/S4306400567","display_name":"Institutional Repository of the University of Granada (University of Granada)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173304897","host_organization_name":"Universidad de Granada","host_organization_lineage":["https://openalex.org/I173304897"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8684520763","display_name":null,"funder_award_id":"PID2019","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4308521110.pdf"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1516787097","https://openalex.org/W1522301498","https://openalex.org/W1568033255","https://openalex.org/W1607435270","https://openalex.org/W1975301756","https://openalex.org/W2119125873","https://openalex.org/W2120847449","https://openalex.org/W2128653836","https://openalex.org/W2138196899","https://openalex.org/W2516001803","https://openalex.org/W2889286744","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2998733532","https://openalex.org/W3025368369","https://openalex.org/W3096408984","https://openalex.org/W3109018774","https://openalex.org/W3126399577","https://openalex.org/W3145029257","https://openalex.org/W3197419241","https://openalex.org/W4307199125"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W2402466562","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2782295999","https://openalex.org/W2162306796","https://openalex.org/W1970292246"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"techniques":[2],"have":[3,124,129],"widely":[4],"been":[5],"applied":[6],"to":[7,26,38,98,115],"speech":[8,34,150],"enhancement":[9],"as":[10,36,138],"they":[11],"show":[12],"outstanding":[13],"modeling":[14],"capa-":[15],"bilities":[16],"that":[17,126],"are":[18,113],"needed":[19],"for":[20,46,64],"proper":[21],"speech-noise":[22],"separation.":[23],"In":[24,51,76],"contrast":[25],"other":[27],"end-to-end":[28],"approaches,":[29,53],"masking-based":[30],"meth-":[31],"ods":[32],"consider":[33],"spectra":[35],"input":[37],"the":[39,54,61,65,81],"deep":[40],"neural":[41,92],"network,":[42],"providing":[43],"spectral":[44],"masks":[45],"noise":[47],"removal":[48],"or":[49],"attenuation.":[50],"these":[52],"Short-Time":[55],"Fourier":[56],"Transform":[57],"(STFT)":[58],"and,":[59],"particularly,":[60],"parameters":[62],"used":[63,114],"analysis/synthesis":[66],"window,":[67],"plays":[68],"an":[69,130],"important":[70],"role":[71],"which":[72,95],"is":[73,96],"often":[74],"neglected.":[75],"this":[77],"paper,":[78],"we":[79,123],"analyze":[80],"effects":[82],"of":[83],"window":[84,135,139],"length":[85],"and":[86,102,108],"shift":[87],"on":[88],"a":[89,120],"complex-domain":[90],"convolutional-recurrent":[91],"network":[93],"(DCCRN)":[94],"able":[97],"provide,":[99],"separately,":[100],"magnitude":[101,147],"phase":[103,127,142],"corrections.":[104],"Different":[105],"perceptual":[106],"quality":[107],"intelligibil-":[109],"ity":[110],"objective":[111],"metrics":[112],"assess":[116],"its":[117],"performance.":[118],"As":[119],"re-":[121],"sult,":[122],"observed":[125],"corrections":[128],"increased":[131],"impact":[132],"with":[133],"shorter":[134],"sizes.":[136],"Similarly,":[137],"overlap":[140],"increases,":[141],"takes":[143],"more":[144],"relevance":[145],"than":[146],"spectrum":[148],"in":[149],"enhancement.":[151]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}