{"id":"https://openalex.org/W4416800181","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249267","title":"MVDR Beamforming for Underdetermined Sound Source Separation using Iterative PSD Estimation in Beamspace","display_name":"MVDR Beamforming for Underdetermined Sound Source Separation using Iterative PSD Estimation in Beamspace","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800181","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249267"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2292/73974","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015985127","display_name":"Jin Xuan Teh","orcid":"https://orcid.org/0009-0007-3887-6613"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]},{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Jin Xuan Teh","raw_affiliation_strings":["Acoustics and Vibration Research Centre, University of Auckland,Auckland,New Zealand"],"affiliations":[{"raw_affiliation_string":"Acoustics and Vibration Research Centre, University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069841141","display_name":"Yusuke Hioka","orcid":"https://orcid.org/0000-0003-3380-9677"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]},{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Yusuke Hioka","raw_affiliation_strings":["Acoustics and Vibration Research Centre, University of Auckland,Auckland,New Zealand"],"affiliations":[{"raw_affiliation_string":"Acoustics and Vibration Research Centre, University of Auckland,Auckland,New Zealand","institution_ids":["https://openalex.org/I154130895","https://openalex.org/I39854758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015985127"],"corresponding_institution_ids":["https://openalex.org/I154130895","https://openalex.org/I39854758"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44728057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9315999746322632,"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":0.9315999746322632,"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":0.03460000082850456,"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":0.005799999926239252,"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":0.7886000275611877},{"id":"https://openalex.org/keywords/underdetermined-system","display_name":"Underdetermined system","score":0.6686999797821045},{"id":"https://openalex.org/keywords/anechoic-chamber","display_name":"Anechoic chamber","score":0.46869999170303345},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.414900004863739},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4074999988079071},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.39980000257492065},{"id":"https://openalex.org/keywords/minimum-variance-unbiased-estimator","display_name":"Minimum-variance unbiased estimator","score":0.38040000200271606},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.36149999499320984}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7886000275611877},{"id":"https://openalex.org/C179690561","wikidata":"https://www.wikidata.org/wiki/Q4316110","display_name":"Underdetermined system","level":2,"score":0.6686999797821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6632999777793884},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.46869999170303345},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4074999988079071},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C165646398","wikidata":"https://www.wikidata.org/wiki/Q3755281","display_name":"Minimum-variance unbiased estimator","level":3,"score":0.38040000200271606},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3407999873161316},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.29989999532699585},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.2732999920845032}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/73974","is_oa":true,"landing_page_url":"https://hdl.handle.net/2292/73974","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"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":"Conference Item"}],"best_oa_location":{"id":"pmh:oai:researchspace.auckland.ac.nz:2292/73974","is_oa":true,"landing_page_url":"https://hdl.handle.net/2292/73974","pdf_url":null,"source":{"id":"https://openalex.org/S7407055463","display_name":"ResearchSpace (University of Auckland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I154130895","host_organization_name":"University of Auckland","host_organization_lineage":["https://openalex.org/I154130895"],"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":"Conference Item"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320801","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W141203745","https://openalex.org/W1987906574","https://openalex.org/W1996304098","https://openalex.org/W2005981242","https://openalex.org/W2031583051","https://openalex.org/W2060108923","https://openalex.org/W2066218102","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2167546860","https://openalex.org/W2938386503","https://openalex.org/W3162341667","https://openalex.org/W3214500491","https://openalex.org/W4249052411","https://openalex.org/W4406844234"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"iterative":[3,101],"beamforming":[4,12,39,109],"framework":[5,22],"that":[6],"combines":[7],"minimum-variance":[8],"distortionless":[9,105],"response":[10,106],"(MVDR)":[11],"with":[13,163],"power":[14],"spectral":[15],"density":[16],"(PSD)":[17],"estimation":[18],"in":[19,28,51,73,93,133],"beamspace.":[20],"This":[21,100],"leverages":[23],"the":[24,29,35,70,79,84,88,96,104,112,150,154],"sparsity":[25],"of":[26,37,47,83,107,157],"speech":[27],"time-frequency":[30,159],"(TF)":[31],"domain":[32],"to":[33,61,143],"improve":[34,95],"performance":[36],"MVDR":[38,63,85,108,160],"for":[40,65,114],"underdetermined":[41],"sound":[42],"source":[43,165],"separation.":[44],"Initially,":[45],"PSD":[46,90],"interferences":[48],"are":[49,59],"estimated":[50],"beamspace":[52],"using":[53],"multiple":[54],"fixed":[55],"beamformers.":[56],"These":[57],"estimates":[58],"used":[60],"compute":[62],"weights":[64],"each":[66,74,77],"TF":[67],"bin,":[68],"attenuating":[69],"dominant":[71],"interferers":[72],"bin.":[75],"In":[76],"iteration,":[78],"enhanced":[80],"spatial":[81],"selectivity":[82],"outputs":[86],"refines":[87],"interference":[89],"estimates,":[91],"which":[92],"turn":[94],"subsequent":[97],"weight":[98],"computations.":[99],"process":[102],"preserves":[103],"while":[110],"eliminating":[111],"need":[113],"nonlinear":[115],"post-filtering":[116],"and":[117,122,137],"its":[118],"associated":[119],"artefacts.":[120],"Simulations":[121],"real-world":[123],"experiments":[124],"conducted":[125],"across":[126],"diverse":[127],"acoustic":[128],"environments":[129],"demonstrate":[130],"substantial":[131],"improvements":[132],"signal-to-interference":[134],"ratio":[135],"(SIR)":[136],"short-time":[138],"objective":[139],"intelligibility":[140],"(STOI)":[141],"compared":[142],"conventional":[144],"MVDR.":[145],"Notably,":[146],"under":[147],"anechoic":[148],"conditions,":[149],"proposed":[151],"method":[152],"approaches":[153],"SIR":[155],"improvement":[156],"a":[158],"beamformer":[161],"constructed":[162],"oracle":[164],"PSD.":[166]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}