{"id":"https://openalex.org/W7134043536","doi":"https://doi.org/10.48550/arxiv.2603.05270","title":"Visual-Informed Speech Enhancement Using Attention-Based Beamforming","display_name":"Visual-Informed Speech Enhancement Using Attention-Based Beamforming","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134043536","doi":"https://doi.org/10.48550/arxiv.2603.05270"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.05270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.05270","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002918513","display_name":"Chihyun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Chihyun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128264900","display_name":"Jiaxuan Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiaxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128219296","display_name":"Mingtung Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Mingtung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128235044","display_name":"Michael Anthony","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anthony, Michael","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064820492","display_name":"Mingsian R. Bai","orcid":"https://orcid.org/0000-0002-8866-106X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Mingsian R.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128264207","display_name":"Yu Tsao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsao, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002918513"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9975000023841858,"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":0.9975000023841858,"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/T11448","display_name":"Face recognition and analysis","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7630000114440918},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7408000230789185},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7063000202178955},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6392999887466431},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5393999814987183},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5273000001907349},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5012999773025513},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4724000096321106}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7630000114440918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7447999715805054},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7408000230789185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297000288963318},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7063000202178955},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6392999887466431},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5012999773025513},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4724000096321106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45669999718666077},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42239999771118164},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4180000126361847},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.05270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.05270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"demonstrated":[3,134],"that":[4,135],"incorporating":[5],"auxiliary":[6],"information,":[7],"such":[8],"as":[9,94],"speaker":[10,106,152],"voiceprint":[11],"or":[12,40,49],"visual":[13,86],"cues,":[14],"can":[15],"substantially":[16],"improve":[17],"Speech":[18],"Enhancement":[19],"(SE)":[20],"performance.":[21],"However,":[22],"single-channel":[23],"methods":[24],"often":[25],"yield":[26],"suboptimal":[27],"results":[28,133],"in":[29,41],"low":[30],"signal-to-noise":[31],"ratio":[32],"(SNR)":[33],"conditions,":[34],"when":[35],"there":[36],"is":[37,110],"high":[38],"reverberation,":[39],"complex":[42],"scenarios":[43],"involving":[44],"dynamic":[45,151],"speakers,":[46],"overlapping":[47],"speech,":[48],"non-stationary":[50],"noise.":[51],"To":[52],"address":[53],"these":[54],"issues,":[55],"we":[56],"propose":[57],"a":[58,84,121],"novel":[59],"Visual-Informed":[60],"Neural":[61],"Beamforming":[62],"Network":[63],"(VI-NBFNet),":[64],"which":[65,97],"integrates":[66],"microphone":[67],"array":[68],"signal":[69],"processing":[70],"and":[71,104,116,145,150],"deep":[72],"neural":[73],"networks":[74],"(DNNs)":[75],"using":[76],"multimodal":[77],"input":[78,95],"features.":[79],"The":[80,108,131],"proposed":[81,137],"network":[82],"leverages":[83],"pretrained":[85],"speech":[87],"recognition":[88],"model":[89],"to":[90,112,155],"extract":[91],"lip":[92],"movements":[93],"features,":[96],"serve":[98],"for":[99,147],"voice":[100],"activity":[101],"detection":[102],"(VAD)":[103],"target":[105],"identification.":[107],"system":[109,139],"intended":[111],"handle":[113],"both":[114,148],"static":[115],"moving":[117],"speakers":[118],"by":[119],"introducing":[120],"supervised":[122],"end-to-end":[123],"beamforming":[124],"framework":[125],"equipped":[126],"with":[127],"an":[128],"attention":[129],"mechanism.":[130],"experimental":[132],"the":[136],"audiovisual":[138],"has":[140],"achieved":[141],"better":[142],"SE":[143],"performance":[144],"robustness":[146],"stationary":[149],"scenarios,":[153],"compared":[154],"several":[156],"baseline":[157],"methods.":[158]},"counts_by_year":[],"updated_date":"2026-03-07T13:43:16.611746","created_date":"2026-03-07T00:00:00"}