{"id":"https://openalex.org/W3174108421","doi":"https://doi.org/10.23919/eusipco54536.2021.9616165","title":"Deep Neural Network Based Low-Latency Speech Separation with Asymmetric Analysis-Synthesis Window Pair","display_name":"Deep Neural Network Based Low-Latency Speech Separation with Asymmetric Analysis-Synthesis Window Pair","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3174108421","doi":"https://doi.org/10.23919/eusipco54536.2021.9616165","mag":"3174108421"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616165","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616165","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5100406235","display_name":"Shanshan Wang","orcid":"https://orcid.org/0000-0001-9530-6958"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Shanshan Wang","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001429662","display_name":"Gaurav Naithani","orcid":"https://orcid.org/0000-0001-6622-6457"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Gaurav Naithani","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland","Tampere University"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100406235"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.8602,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7743452,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"305"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7899940013885498},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7417299151420593},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6394801735877991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5754587054252625},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5636591911315918},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.530040979385376},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4503980875015259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41961008310317993},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36278751492500305},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08775684237480164},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07519873976707458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899940013885498},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7417299151420593},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6394801735877991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5754587054252625},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5636591911315918},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.530040979385376},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4503980875015259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41961008310317993},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36278751492500305},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08775684237480164},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07519873976707458}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616165","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616165","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W88987024","https://openalex.org/W1482149378","https://openalex.org/W1502398685","https://openalex.org/W1522301498","https://openalex.org/W1970308149","https://openalex.org/W2020307986","https://openalex.org/W2026285232","https://openalex.org/W2031647436","https://openalex.org/W2038724679","https://openalex.org/W2067295501","https://openalex.org/W2087774313","https://openalex.org/W2112482982","https://openalex.org/W2127851351","https://openalex.org/W2143317947","https://openalex.org/W2156876426","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2798405286","https://openalex.org/W2886515811","https://openalex.org/W2890111732","https://openalex.org/W2891405874","https://openalex.org/W2894649632","https://openalex.org/W2899771611","https://openalex.org/W2916618641","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2964121744","https://openalex.org/W3099330747","https://openalex.org/W4289429458","https://openalex.org/W4293248946","https://openalex.org/W6629956514","https://openalex.org/W6631190155","https://openalex.org/W6681467895","https://openalex.org/W6683161558","https://openalex.org/W6688843265","https://openalex.org/W6754780006","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"Time-frequency":[0],"masking":[1],"or":[2,56],"spectrum":[3],"prediction":[4],"computed":[5],"via":[6],"short":[7],"symmetric":[8],"windows":[9],"are":[10],"commonly":[11],"used":[12],"in":[13,93,101],"low-latency":[14,48],"deep":[15,78],"neural":[16],"network":[17],"(DNN)":[18],"based":[19],"source":[20],"separation.":[21],"In":[22,60],"this":[23],"paper,":[24],"we":[25,72],"propose":[26],"the":[27,47],"use":[28],"of":[29,96,103,112],"an":[30,91,109],"asymmetric":[31],"analysis-synthesis":[32],"window":[33],"pair":[34],"which":[35],"allows":[36],"for":[37,52],"training":[38],"with":[39,41,75],"targets":[40],"better":[42],"frequency":[43],"resolution,":[44],"while":[45,107],"retaining":[46],"during":[49],"inference":[50,86],"suitable":[51],"real-time":[53],"speech":[54],"enhancement":[55],"assisted":[57],"hearing":[58],"applications.":[59],"order":[61],"to":[62,98],"assess":[63],"our":[64],"approach":[65],"across":[66],"various":[67],"model":[68,81],"types":[69],"and":[70,82],"datasets,":[71],"evaluate":[73],"it":[74],"a":[76,83],"speaker-independent":[77],"clustering":[79],"(DC)":[80],"speaker-dependent":[84],"mask":[85],"(MI)":[87],"model.":[88],"We":[89],"report":[90],"improvement":[92],"separation":[94],"performance":[95],"up":[97],"1.5":[99],"dB":[100],"terms":[102],"source-to-distortion":[104],"ratio":[105],"(SDR)":[106],"maintaining":[108],"algorithmic":[110],"latency":[111],"8":[113],"ms.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}