{"id":"https://openalex.org/W4409727705","doi":"https://doi.org/10.1186/s13636-025-00404-7","title":"Single-microphone speaker separation and voice activity detection in noisy and reverberant environments","display_name":"Single-microphone speaker separation and voice activity detection in noisy and reverberant environments","publication_year":2025,"publication_date":"2025-04-23","ids":{"openalex":"https://openalex.org/W4409727705","doi":"https://doi.org/10.1186/s13636-025-00404-7"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00404-7","doi":"https://doi.org/10.1186/s13636-025-00404-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00404-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00404-7","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,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","poland-100","russia-white-list-2","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00404-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084760213","display_name":"Renana Opochinsky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Renana Opochinsky","raw_affiliation_strings":["Faculty of Engineering, Bar Ilan University, Ramat-Gan, 5290002, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar Ilan University, Ramat-Gan, 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003299821","display_name":"Mordehay Moradi","orcid":"https://orcid.org/0009-0000-1190-0555","observed_orcids":["https://orcid.org/0009-0000-1190-0555"]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Mordehay Moradi","raw_affiliation_strings":["Faculty of Engineering, Bar Ilan University, Ramat-Gan, 5290002, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar Ilan University, Ramat-Gan, 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X","observed_orcids":["https://orcid.org/0000-0002-2885-170X"]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["Faculty of Engineering, Bar Ilan University, Ramat-Gan, 5290002, Israel"],"raw_orcid":"https://orcid.org/0000-0002-2885-170X","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar Ilan University, Ramat-Gan, 5290002, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001052072"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":{"value":1890,"currency":"USD","value_usd":1890},"apc_paid":{"value":1890,"currency":"USD","value_usd":1890},"fwci":2.8807,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90594213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9922000169754028,"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":0.9922000169754028,"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":0.006500000134110451,"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":0.0007999999797903001,"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/voice-activity-detection","display_name":"voice activity detection","score":0.8180000185966492},{"id":"https://openalex.org/keywords/time-frequency-attention","display_name":"time-frequency attention","score":0.8420000076293945},{"id":"https://openalex.org/keywords/temporal-convolutional-network","display_name":"temporal convolutional network","score":0.8379999995231628},{"id":"https://openalex.org/keywords/conv-tasnet","display_name":"Conv-TasNet","score":0.8309999704360962},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"short-time Fourier transform","score":0.890999972820282},{"id":"https://openalex.org/keywords/noisy-environments","display_name":"noisy environments","score":0.6060000061988831},{"id":"https://openalex.org/keywords/overlapping-speech","display_name":"overlapping speech","score":0.7120000123977661},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.8709999918937683},{"id":"https://openalex.org/keywords/block-processing","display_name":"block processing","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8497915267944336},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8190932869911194},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6476032137870789},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6226726770401001},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.543340802192688},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.49823689460754395},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4554833769798279},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42411476373672485},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3804475963115692},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.18954089283943176},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.17768791317939758},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05534026026725769},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13636-025-00404-7","doi":"https://doi.org/10.1186/s13636-025-00404-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00404-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00404-7","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,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","poland-100","russia-white-list-2","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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:arXiv.org:2401.03448","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.03448","pdf_url":"https://arxiv.org/pdf/2401.03448","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:doaj.org/article:8b4c031405c240ca95eab55f7aeb3f56","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/8b4c031405c240ca95eab55f7aeb3f56","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,"listed_in":[],"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 2025, Iss 1, Pp 1-16 (2025)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2401.03448","doi":"https://doi.org/10.48550/arxiv.2401.03448","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.03448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00404-7","doi":"https://doi.org/10.1186/s13636-025-00404-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00404-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00404-7","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,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","norway-1","poland-100","russia-white-list-2","vabb-shw"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7556389956","display_name":null,"funder_award_id":"871245","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8258793481","display_name":"Socially Pertinent Robots in Gerontological Healthcare","funder_award_id":"871245","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320319290","display_name":"Meta","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320324256","display_name":"Y\u00fcksek\u00f6\u011fretim Kurulu","ror":"https://ror.org/00j1q0b46"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335375","display_name":"Planning and Budgeting Committee of the Council for Higher Education of Israel","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409727705.pdf","grobid_xml":"https://content.openalex.org/works/W4409727705.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1989314204","https://openalex.org/W2103825654","https://openalex.org/W2117678320","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2510642588","https://openalex.org/W2734774145","https://openalex.org/W2891004713","https://openalex.org/W2900368655","https://openalex.org/W2952218014","https://openalex.org/W2954031873","https://openalex.org/W2981541003","https://openalex.org/W2990899015","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015661721","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3042857426","https://openalex.org/W3116570699","https://openalex.org/W3133848124","https://openalex.org/W3135285714","https://openalex.org/W3160747466","https://openalex.org/W3163652268","https://openalex.org/W3169940635","https://openalex.org/W3213661887","https://openalex.org/W4225302959","https://openalex.org/W4296068589","https://openalex.org/W4311187069","https://openalex.org/W4312271884","https://openalex.org/W4372260572","https://openalex.org/W4375869348","https://openalex.org/W4385756463","https://openalex.org/W4392903251","https://openalex.org/W6605023316"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W1977167953","https://openalex.org/W107154053","https://openalex.org/W2122030153","https://openalex.org/W2162449135"],"abstract_inverted_index":{"The":[0,69,211],"increasing":[1],"complexity":[2],"of":[3,15,53,90,146,195,220],"real-world":[4,151,164],"environments,":[5],"where":[6],"multiple":[7],"speakers":[8],"might":[9],"converse":[10],"simultaneously,":[11],"underscores":[12],"the":[13,54,66,83,99,159,172,196,231],"importance":[14],"effective":[16],"speech":[17,137,148],"separation":[18,26,55,67,70],"techniques.":[19],"This":[20],"work":[21],"presents":[22],"a":[23,51,60,75,92,181,190],"single-microphone":[24,191],"speaker":[25],"network":[27,78],"with":[28,86],"time-frequency":[29],"(TF)":[30],"attention":[31],"aimed":[32],"at":[33,175,216],"noisy":[34],"and":[35,95,104,112,123,178,202,218],"reverberant":[36],"environments.":[37],"We":[38],"dub":[39],"this":[40,155,185,200,225],"new":[41],"architecture":[42],"Separation":[43],"TF":[44],"Attention":[45],"Network":[46],"(Sep-TFAnet).":[47],"Additionally,":[48],"we":[49,97,157,187],"introduce":[50,158],"variant":[52],"network,":[56],"Sep-TFAnetVAD,":[57],"which":[58,162],"incorporates":[59,163],"voice":[61],"activity":[62],"detector":[63],"(VAD)":[64],"into":[65],"network.":[68],"module":[71],"is":[72,117,214],"based":[73],"on":[74,144,189,230],"temporal":[76],"convolutional":[77],"(TCN)":[79],"backbone":[80],"inspired":[81],"by":[82,180],"Conv-Tasnet":[84],"architecture,":[85],"several":[87],"modifications.":[88],"Instead":[89],"using":[91,199],"learned":[93],"encoder":[94],"decoder,":[96],"employ":[98],"short-time":[100,106],"Fourier":[101,107],"transform":[102,108],"(STFT)":[103],"inverse":[105],"(iSTFT)":[109],"for":[110,120],"analysis":[111],"synthesis,":[113],"respectively.":[114],"Our":[115],"system":[116],"specifically":[118],"developed":[119],"human-robot":[121],"interaction":[122],"supports":[124],"block":[125],"processing":[126],"mode.":[127],"While":[128],"considerable":[129],"progress":[130],"has":[131],"been":[132],"made":[133],"in":[134,171],"separating":[135],"overlapping":[136],"signals,":[138,149],"most":[139],"studies":[140],"have":[141],"primarily":[142],"focused":[143],"mixtures":[145],"simulated-reverberated":[147],"lacking":[150],"scenarios.":[152],"To":[153],"address":[154],"limitation,":[156],"ARImulti-mic":[160,212],"dataset,":[161],"experiments.":[165],"These":[166],"recordings":[167],"were":[168],"carried":[169],"out":[170],"acoustic":[173],"laboratory":[174],"Bar-Ilan":[176],"University":[177],"captured":[179],"humanoid":[182],"robot.":[183],"Throughout":[184],"paper,":[186],"focus":[188],"setting.":[192],"Extensive":[193],"evaluation":[194],"proposed":[197],"methods":[198],"dataset":[201,213,226],"carefully":[203],"simulated":[204],"data":[205],"demonstrated":[206],"advantages":[207],"over":[208],"competing":[209],"methods.":[210],"available":[215],"DataPort,":[217],"examples":[219],"our":[221],"algorithm":[222],"applied":[223],"to":[224],"can":[227],"be":[228],"found":[229],"project":[232],"page:":[233],"https://Sep-TFAnet.github.io":[234],".":[235]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}
