{"id":"https://openalex.org/W7220975868","doi":"https://doi.org/10.48550/arxiv.2610.09334","title":"VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation","display_name":"VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech Separation","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220975868","doi":"https://doi.org/10.48550/arxiv.2610.09334"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09334","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09334","pdf_url":"https://arxiv.org/pdf/2610.09334","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125549652","display_name":"Jingqi Sun","orcid":"https://orcid.org/0009-0009-2466-0357","observed_orcids":["https://orcid.org/0009-0009-2466-0357"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Jingqi","raw_affiliation_strings":["Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029366297","display_name":"Haozhan Tang","orcid":"https://orcid.org/0000-0001-6719-846X","observed_orcids":["https://orcid.org/0000-0001-6719-846X"]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Haozhan","raw_affiliation_strings":["Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157946275","display_name":"Shulin He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Shulin","raw_affiliation_strings":["Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157916786","display_name":"Zhong-Qiu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhong-Qiu","raw_affiliation_strings":["Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9779999852180481,"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":0.9779999852180481,"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":0.016899999231100082,"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":0.002099999925121665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/blind-source-separation","display_name":"blind source separation","score":0.9120000004768372},{"id":"https://openalex.org/keywords/virtual-microphones","display_name":"virtual microphones","score":0.7670000195503235},{"id":"https://openalex.org/keywords/microphone-array","display_name":"microphone array","score":0.7020000219345093},{"id":"https://openalex.org/keywords/diffusion-posterior-sampling","display_name":"diffusion posterior sampling","score":0.7749999761581421},{"id":"https://openalex.org/keywords/acoustic-transfer-function","display_name":"acoustic transfer function","score":0.7770000100135803},{"id":"https://openalex.org/keywords/independent-vector-analysis","display_name":"independent vector analysis","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8288000226020813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7516999840736389},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.6510999798774719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5674999952316284},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4083000123500824},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.3774000108242035},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.3546999990940094},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3352000117301941},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2685000002384186}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09334","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09334","pdf_url":"https://arxiv.org/pdf/2610.09334","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.09334","doi":"https://doi.org/10.48550/arxiv.2610.09334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09334","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09334","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09334","pdf_url":"https://arxiv.org/pdf/2610.09334","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220975868.pdf","grobid_xml":"https://content.openalex.org/works/W7220975868.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416644560","https://openalex.org/W4415281256","https://openalex.org/W70106411","https://openalex.org/W2135078705","https://openalex.org/W2032917599","https://openalex.org/W7099986397","https://openalex.org/W1497108216","https://openalex.org/W2036490405","https://openalex.org/W7163112516","https://openalex.org/W4416798600"],"abstract_inverted_index":{"Blind":[0],"Source":[1],"Separation(BSS)":[2],"is":[3,89,121],"a":[4,48,63,69,137],"fundamental":[5],"problem":[6,61],"in":[7,118,183],"signal":[8],"processing,":[9],"aiming":[10],"to":[11,74,101,157,192],"separate":[12],"multiple":[13],"source":[14,80,99],"signals":[15,100],"from":[16],"their":[17],"mixtures":[18,106],"without":[19],"prior":[20],"knowledge":[21],"of":[22,40,78,116,128,179,196,199,204],"the":[23,26,76,90,97,103,108,114,119,126,142,159,177,194,197,205],"sources":[24],"or":[25],"mixing":[27],"process.":[28],"Traditional":[29],"approaches,":[30],"such":[31],"as":[32,47,62],"Independent":[33],"Vector":[34],"Analysis":[35],"(IVA)":[36],"exploits":[37],"statistical":[38],"independence":[39],"sources.":[41],"Recently,":[42],"diffusion-based":[43],"approaches":[44],"have":[45],"emerged":[46],"promising":[49],"alternative":[50],"by":[51,209],"leveraging":[52],"powerful":[53],"generative":[54],"priors.":[55],"Among":[56],"them,":[57],"ArrayDPS":[58,169],"formulates":[59],"BSS":[60,185],"posterior":[64],"sampling":[65],"problem,":[66],"and":[67,173,202],"utilizes":[68],"pretrained":[70],"speech":[71],"diffusion":[72],"model":[73],"guide":[75],"recovery":[77],"clean":[79],"signals.":[81],"A":[82],"key":[83],"factor":[84],"behind":[85],"its":[86],"separation":[87,160],"capability":[88],"multi-channel":[91],"consistency":[92],"(MC)":[93],"objective,":[94],"which":[95,124],"enforces":[96],"estimated":[98,109],"reconstruct":[102],"observed":[104],"microphone":[105,143,181],"through":[107],"acoustic":[110],"transfer":[111],"functions.":[112],"However,":[113],"number":[115,198],"microphones":[117,147,151,201],"array":[120,144],"often":[122],"limited,":[123],"constrains":[125],"performance":[127],"ArrayDPS.":[129],"To":[130],"address":[131],"this":[132],"issue,":[133],"we":[134],"propose":[135],"VM-ArrayDPS,":[136],"novel":[138],"method":[139],"that":[140,165],"augments":[141],"with":[145,148],"virtual":[146,180,200,210],"higher-SNR,":[149],"these":[150],"can":[152],"offer":[153],"extra":[154],"MC":[155,206],"constraints":[156],"enhance":[158],"performance.":[161,186],"Experimental":[162],"results":[163],"demonstrate":[164],"VM-ArrayDPS":[166],"significantly":[167],"outperforms":[168],"on":[170],"both":[171],"2-speaker":[172],"3-speaker":[174],"datasets,":[175],"showcasing":[176],"effectiveness":[178],"augmentation":[182],"improving":[184],"We":[187],"also":[188],"did":[189],"ablation":[190],"studies":[191],"show":[193],"influence":[195],"weight":[203],"objective":[207],"brought":[208],"microphones.":[211]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-09T00:00:00"}