{"id":"https://openalex.org/W7214730945","doi":"https://doi.org/10.48550/arxiv.2609.31708","title":"RadarVox: Radar-Audio Multimodal Cocktail-Party Speech Separation with Speaker-Aware Cross-Modal Matching","display_name":"RadarVox: Radar-Audio Multimodal Cocktail-Party Speech Separation with Speaker-Aware Cross-Modal Matching","publication_year":2026,"publication_date":"2026-09-20","ids":{"openalex":"https://openalex.org/W7214730945","doi":"https://doi.org/10.48550/arxiv.2609.31708"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.31708","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31708","pdf_url":"https://arxiv.org/pdf/2609.31708","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.31708","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147432203","display_name":"Yanlin Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Yanlin","raw_affiliation_strings":["New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031051208","display_name":"Yiwei Ru","orcid":"https://orcid.org/0009-0004-5577-2769","observed_orcids":["https://orcid.org/0009-0004-5577-2769"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru, Yiwei","raw_affiliation_strings":["New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072011997","display_name":"Mupei Li","orcid":"https://orcid.org/0009-0004-4773-8448","observed_orcids":["https://orcid.org/0009-0004-4773-8448"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Mupei","raw_affiliation_strings":["New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084959030","display_name":"Yongji Liu","orcid":"https://orcid.org/0009-0008-6756-9011","observed_orcids":["https://orcid.org/0009-0008-6756-9011"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yongji","raw_affiliation_strings":["New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153485151","display_name":"Jie Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jie","raw_affiliation_strings":["New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recog- nition (NLPR) , State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) , Institute of Automation , Chinese Academy of Sciences (CASIA) , Beijing 100190 , China,","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153548128","display_name":"Zhenan Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zhenan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9818999767303467,"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":0.9818999767303467,"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/T11309","display_name":"Music and Audio Processing","score":0.005900000222027302,"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":0.005100000184029341,"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/speaker-attribution","display_name":"speaker attribution","score":0.6660000085830688},{"id":"https://openalex.org/keywords/fmcw-radar","display_name":"FMCW radar","score":0.9110000133514404},{"id":"https://openalex.org/keywords/permutation-ambiguity","display_name":"permutation ambiguity","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7024999856948853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6589999794960022},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5665000081062317},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4074999988079071},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.37619999051094055},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.2976999878883362},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.26269999146461487},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.31708","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31708","pdf_url":"https://arxiv.org/pdf/2609.31708","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.31708","doi":"https://doi.org/10.48550/arxiv.2609.31708","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.31708","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.31708","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31708","pdf_url":"https://arxiv.org/pdf/2609.31708","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214730945.pdf","grobid_xml":"https://content.openalex.org/works/W7214730945.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3128634009","https://openalex.org/W4321600175","https://openalex.org/W4384303965","https://openalex.org/W3016048045","https://openalex.org/W2612083379","https://openalex.org/W4401609738","https://openalex.org/W2282641350","https://openalex.org/W2973062255","https://openalex.org/W2768808476","https://openalex.org/W2981992480"],"abstract_inverted_index":{"In":[0],"embodied":[1],"voice":[2],"interaction,":[3],"cocktail-party":[4,49],"speech":[5,9,18,50,105],"perception":[6],"requires":[7],"both":[8],"separation":[10,25],"and":[11,16,35,56,63,96,130,135],"speaker":[12,68,159],"attribution":[13],"across":[14],"machine-generated":[15],"human":[17,64],"sources.":[19],"However,":[20],"conventional":[21],"audio-only":[22,153],"blind":[23],"source":[24],"remains":[26],"permutation":[27],"ambiguous,":[28],"making":[29],"the":[30,141],"correspondence":[31],"between":[32],"separated":[33],"streams":[34,106],"physical":[36],"speakers":[37],"unclear.":[38],"This":[39],"paper":[40],"presents":[41],"RadarVox,":[42],"a":[43,82,90,98],"radar-audio":[44],"multimodal":[45],"benchmark":[46],"for":[47],"identity-aware":[48],"separation.":[51],"RadarVox":[52],"provides":[53],"acoustic":[54],"mixtures":[55,113],"source-level":[57],"radar":[58,71,116],"displacement":[59],"signals":[60],"from":[61],"loudspeaker-emitted":[62],"speech,":[65],"enabling":[66],"source-aware":[67],"assignment.":[69],"FMCW":[70],"captures":[72],"laryngeal":[73],"mechanical":[74],"motion,":[75],"providing":[76],"speaker-specific":[77],"spatial-motion":[78],"cues":[79,117],"unavailable":[80],"to":[81,102],"single-channel":[83],"microphone.":[84],"We":[85],"inject":[86],"radar-derived":[87],"priors":[88],"into":[89],"DPRNN":[91],"separator":[92],"via":[93],"gated":[94],"fusion":[95],"learn":[97],"speaker-aware":[99],"cross-modal":[100],"matcher":[101],"associate":[103],"unordered":[104],"with":[107],"radar-observed":[108],"speakers.":[109],"Experiments":[110],"on":[111],"multi-speaker":[112],"show":[114],"that":[115],"provide":[118],"complementary":[119],"benefits,":[120],"achieving":[121,156],"scale-invariant":[122],"signal-to-distortion":[123],"ratio":[124],"(SI-SDR)":[125],"values":[126],"of":[127],"9.75":[128],"dB":[129,132,151],"7.13":[131],"in":[133],"two-":[134],"three-speaker":[136],"scenarios,":[137],"respectively.":[138],"More":[139],"importantly,":[140],"proposed":[142],"method":[143],"improves":[144],"ordered":[145],"SI-SDR":[146],"by":[147],"more":[148],"than":[149],"13":[150],"over":[152,157],"methods":[154],"while":[155],"80\\%":[158],"assignment":[160],"accuracy.":[161]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-30T00:00:00"}