{"id":"https://openalex.org/W3015233996","doi":"https://doi.org/10.1109/icassp40776.2020.9053649","title":"Geometrically Constrained Independent Vector Analysis for Directional Speech Enhancement","display_name":"Geometrically Constrained Independent Vector Analysis for Directional Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015233996","doi":"https://doi.org/10.1109/icassp40776.2020.9053649","mag":"3015233996"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100361230","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-7163-6263"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Li Li","raw_affiliation_strings":["University of Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100361230"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":2.5761,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.90138249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"846","last_page":"850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9980999827384949,"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/beamforming","display_name":"Beamforming","score":0.7623774409294128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.744846522808075},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6540290117263794},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6381121277809143},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.560210108757019},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5520687699317932},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5501915216445923},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5270369648933411},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5141661167144775},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5072652697563171},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4958537518978119},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44539809226989746},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4426461458206177},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4241832494735718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.370887815952301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2018771469593048},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14301389455795288},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.1133858859539032},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09548938274383545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08866313099861145}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7623774409294128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744846522808075},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6540290117263794},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6381121277809143},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.560210108757019},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5520687699317932},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5501915216445923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5270369648933411},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5141661167144775},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5072652697563171},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4958537518978119},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44539809226989746},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4426461458206177},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4241832494735718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.370887815952301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2018771469593048},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14301389455795288},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.1133858859539032},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09548938274383545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08866313099861145},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"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},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053649","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W653761051","https://openalex.org/W1488610917","https://openalex.org/W1495679096","https://openalex.org/W1543386260","https://openalex.org/W1572099565","https://openalex.org/W1845880232","https://openalex.org/W2019426094","https://openalex.org/W2027884847","https://openalex.org/W2072548008","https://openalex.org/W2113145093","https://openalex.org/W2117678320","https://openalex.org/W2121756139","https://openalex.org/W2127851351","https://openalex.org/W2134910060","https://openalex.org/W2138730076","https://openalex.org/W2145563317","https://openalex.org/W2149414429","https://openalex.org/W2159956319","https://openalex.org/W2161270956","https://openalex.org/W2400273387","https://openalex.org/W2408629183","https://openalex.org/W2485273068","https://openalex.org/W2568308529","https://openalex.org/W2610428556","https://openalex.org/W2792498316","https://openalex.org/W2808718747","https://openalex.org/W2962772442","https://openalex.org/W2963035245","https://openalex.org/W3209141406","https://openalex.org/W4253928870","https://openalex.org/W6629147628","https://openalex.org/W6632571750","https://openalex.org/W6678799340","https://openalex.org/W6681259398","https://openalex.org/W6683607893","https://openalex.org/W6712944358","https://openalex.org/W6714614974","https://openalex.org/W6731182777","https://openalex.org/W6737477478","https://openalex.org/W6765580492","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W1879255185","https://openalex.org/W2031820693","https://openalex.org/W2889447638","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1910172735","https://openalex.org/W1980506188","https://openalex.org/W2107364365","https://openalex.org/W1510462426"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,21,30,45,52,56,68,97,112,116,120],"multichannel":[4],"directional":[5,33],"speech":[6,54,92],"enhancement":[7,93],"problem":[8],"with":[9,104],"geometrically":[10],"constrained":[11],"independent":[12],"vector":[13],"analysis":[14],"(GCIVA),":[15],"where":[16],"we":[17],"aim":[18],"to":[19,50,55,75],"combine":[20],"high":[22],"separation":[23,28],"performance":[24],"from":[25,35,44,67],"blind":[26],"source":[27],"and":[29,84,100,119,131],"capability":[31],"of":[32,48,70,78,129],"focus":[34],"beamforming.":[36],"The":[37,107],"proposed":[38,98,113],"method":[39,99],"exploits":[40],"geometric":[41],"constraints":[42],"composed":[43],"spatial":[46],"information":[47],"sources":[49],"guide":[51],"target":[53],"desired":[57],"output":[58],"channel.":[59],"A":[60],"convergence-guaranteed":[61],"parameter":[62],"estimation":[63],"algorithm":[64],"is":[65],"derived":[66],"framework":[69],"auxiliary":[71],"function-based":[72],"IVA":[73],"(AuxIVA)":[74],"take":[76],"advantage":[77],"fast":[79],"convergence,":[80],"low":[81],"computational":[82],"cost,":[83],"no":[85],"step-size":[86],"tuning.":[87],"We":[88],"propose":[89],"a":[90,124],"dual-microphone":[91],"system":[94,114],"based":[95],"on":[96],"investigate":[101],"its":[102],"effectiveness":[103],"objective":[105],"metrics.":[106],"experimental":[108],"evaluations":[109],"revealed":[110],"that":[111],"outperformed":[115],"conventional":[117],"beamforming":[118],"standard":[121],"AuxIVA":[122],"in":[123,127],"large":[125],"margin":[126],"terms":[128],"source-to-distortion":[130],"source-to-interference":[132],"ratios.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}