{"id":"https://openalex.org/W4403231528","doi":"https://doi.org/10.1186/s13636-024-00373-3","title":"DOA-informed switching independent vector extraction and beamforming for speech enhancement in underdetermined situations","display_name":"DOA-informed switching independent vector extraction and beamforming for speech enhancement in underdetermined situations","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403231528","doi":"https://doi.org/10.1186/s13636-024-00373-3"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00373-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00373-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00373-3","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"],"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/s13636-024-00373-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103194936","display_name":"T. Ueda","orcid":"https://orcid.org/0009-0007-0158-6356"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tetsuya Ueda","raw_affiliation_strings":["Waseda University, 2-7 Hibikino, Wakamatsu-ku, Kita-Kyushu, 808-0135, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0009-0007-0158-6356","affiliations":[{"raw_affiliation_string":"Waseda University, 2-7 Hibikino, Wakamatsu-ku, Kita-Kyushu, 808-0135, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084590882","display_name":"Rintaro Ikeshita","orcid":"https://orcid.org/0000-0003-2608-1999"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rintaro Ikeshita","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["Waseda University, 2-7 Hibikino, Wakamatsu-ku, Kita-Kyushu, 808-0135, Fukuoka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University, 2-7 Hibikino, Wakamatsu-ku, Kita-Kyushu, 808-0135, Fukuoka, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103194936"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.215,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47104643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2024","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":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/T11447","display_name":"Blind Source Separation Techniques","score":0.9997000098228455,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9994999766349792,"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/underdetermined-system","display_name":"Underdetermined system","score":0.9135551452636719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8737217783927917},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7124365568161011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5055837631225586},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.48019349575042725},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.47088488936424255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31270134449005127},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27645623683929443},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16528752446174622}],"concepts":[{"id":"https://openalex.org/C179690561","wikidata":"https://www.wikidata.org/wiki/Q4316110","display_name":"Underdetermined system","level":2,"score":0.9135551452636719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8737217783927917},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7124365568161011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5055837631225586},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.48019349575042725},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.47088488936424255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31270134449005127},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27645623683929443},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16528752446174622},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00373-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00373-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00373-3","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"],"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:de6dfe3191c04d4e8c5ae94f52bbb48e","is_oa":true,"landing_page_url":"https://doaj.org/article/de6dfe3191c04d4e8c5ae94f52bbb48e","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 2024, Iss 1, Pp 1-20 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00373-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00373-3","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-024-00373-3","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"],"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":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2069546884","display_name":"\u97f3\u74b0\u5883\u306e\u8a8d\u8b58\u3068\u7406\u89e3\u306e\u305f\u3081\u306e\u9769\u65b0\u7684\u30de\u30a4\u30af\u30ed\u30db\u30f3\u30a2\u30ec\u30fc\u57fa\u76e4\u6280\u8853\u306e\u6df1\u5316","funder_award_id":"23K28113","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8856149045","display_name":null,"funder_award_id":"JPMJSP2128","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403231528.pdf","grobid_xml":"https://content.openalex.org/works/W4403231528.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W108815450","https://openalex.org/W1543386260","https://openalex.org/W1552314771","https://openalex.org/W2019426094","https://openalex.org/W2060108923","https://openalex.org/W2071795835","https://openalex.org/W2114461480","https://openalex.org/W2117678320","https://openalex.org/W2123649031","https://openalex.org/W2134910060","https://openalex.org/W2144244295","https://openalex.org/W2289394825","https://openalex.org/W2400273387","https://openalex.org/W2808718747","https://openalex.org/W2902777576","https://openalex.org/W2905402910","https://openalex.org/W2951431217","https://openalex.org/W2964058413","https://openalex.org/W2966098955","https://openalex.org/W2989287578","https://openalex.org/W2997688633","https://openalex.org/W3000508686","https://openalex.org/W3015233996","https://openalex.org/W3015306655","https://openalex.org/W3093410526","https://openalex.org/W3095940219","https://openalex.org/W3105118415","https://openalex.org/W3128534387","https://openalex.org/W3185812430","https://openalex.org/W4205167030","https://openalex.org/W4312307927","https://openalex.org/W4388821144"],"related_works":["https://openalex.org/W133751542","https://openalex.org/W2066796569","https://openalex.org/W2997320962","https://openalex.org/W4287906532","https://openalex.org/W3011121006","https://openalex.org/W176802781","https://openalex.org/W2084978503","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Abstract":[0],"This":[1,128],"paper":[2,129],"proposes":[3],"novel":[4],"methods":[5,133,179,197],"for":[6],"extracting":[7,37],"a":[8,16,83,95,141],"single":[9],"Speech":[10],"signal":[11,19,27],"of":[12,43,47],"Interest":[13],"(SOI)":[14],"from":[15],"multichannel":[17],"observed":[18,26],"in":[20,67,125,173,198,205],"underdetermined":[21,80,126,174,206],"situations,":[22],"i.e.,":[23],"when":[24,91],"the":[25,38,44,100,111,152,157,162,200,203],"contains":[28],"more":[29],"speech":[30,65,170],"signals":[31,66],"than":[32],"microphones.":[33],"It":[34],"focuses":[35],"on":[36,94,115,156],"SOI":[39,112,153,201],"using":[40,82,118,202],"prior":[41],"knowledge":[42],"SOI\u2019s":[45,101],"Direction":[46],"Arrival":[48],"(DOA).":[49],"Conventional":[50],"beamformers":[51],"(BFs)":[52],"and":[53,186],"Blind":[54],"Source":[55],"Separation":[56],"(BSS)":[57],"with":[58],"spatial":[59,119],"regularization":[60],"struggle":[61],"to":[62,134,147,149,165,167],"suppress":[63],"interference":[64],"such":[68],"situations.":[69,127,175,207],"Although":[70],"Switching":[71,182,187],"Minimum":[72],"Power":[73],"Distortionless":[74],"Response":[75],"BF":[76],"(Sw-MPDR)":[77],"can":[78,108],"handle":[79],"situations":[81],"switching":[84,163],"mechanism,":[85],"its":[86,116,122,169],"estimation":[87],"accuracy":[88],"significantly":[89],"decreases":[90],"it":[92],"relies":[93],"steering":[96],"vector":[97],"determined":[98],"by":[99],"DOA.":[102,158],"Spatially-Regularized":[103],"Independent":[104],"Vector":[105],"Extraction":[106],"(SRIVE)":[107],"robustly":[109],"enhance":[110,151],"based":[113,154],"solely":[114,155],"DOA":[117,204],"regularization,":[120],"but":[121],"performance":[123,172],"degrades":[124],"extends":[130],"these":[131],"conventional":[132,196],"overcome":[135],"their":[136],"limitations.":[137],"First,":[138],"we":[139,160],"introduce":[140,161],"time-varying":[142],"Gaussian":[143],"(TVG)":[144],"source":[145],"model":[146],"Sw-MPDR":[148],"effectively":[150],"Second,":[159],"mechanism":[164],"SRIVE":[166,188],"improve":[168],"enhancement":[171],"These":[176],"two":[177],"proposed":[178],"are":[180],"called":[181],"weighted":[183],"MPDR":[184],"(Sw-wMPDR)":[185],"(Sw-SRIVE).":[189],"We":[190],"experimentally":[191],"demonstrate":[192],"that":[193],"both":[194],"surpass":[195],"enhancing":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}