{"id":"https://openalex.org/W4226140507","doi":"https://doi.org/10.48550/arxiv.2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","display_name":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","publication_year":2022,"publication_date":"2022-03-04","ids":{"openalex":"https://openalex.org/W4226140507","doi":"https://doi.org/10.48550/arxiv.2203.02216"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2203.02216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02216","pdf_url":"https://arxiv.org/pdf/2203.02216","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.02216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiong, Junwen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiong, Junwen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038150414","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-3723-7584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364263","display_name":"Peng Zhang","orcid":"https://orcid.org/0009-0000-3326-4983"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365442","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-2994-6743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Lei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352881","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0001-7004-6408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014604035","display_name":"Yufei Zha","orcid":"https://orcid.org/0000-0001-5013-2501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zha, Yufei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"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":0.9998999834060669,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9861999750137329,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9811000227928162,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7877244353294373},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6548849940299988},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6181789040565491},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6063655018806458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5771767497062683},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5573806762695312},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4788808226585388},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4599321186542511},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4470248520374298},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4290618598461151},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4152616858482361},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09576943516731262},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07092064619064331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7877244353294373},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6548849940299988},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6181789040565491},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6063655018806458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5771767497062683},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5573806762695312},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4788808226585388},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4599321186542511},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4470248520374298},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4290618598461151},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4152616858482361},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09576943516731262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07092064619064331},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2203.02216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02216","pdf_url":"https://arxiv.org/pdf/2203.02216","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.02216","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.02216","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":"pmh:oai:arXiv.org:2203.02216","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02216","pdf_url":"https://arxiv.org/pdf/2203.02216","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W4301248618","https://openalex.org/W2165343651","https://openalex.org/W2242427765","https://openalex.org/W2075830955","https://openalex.org/W2343790552","https://openalex.org/W3111398917","https://openalex.org/W4385507578","https://openalex.org/W2949157572"],"abstract_inverted_index":{"Active":[0],"speaker":[1,110],"detection":[2,111],"and":[3,49,76,112],"speech":[4,113],"enhancement":[5,114],"have":[6,68],"become":[7],"two":[8],"increasingly":[9],"attractive":[10],"topics":[11],"in":[12,31,52,99,121],"audio-visual":[13,87,100,119],"scenario":[14],"understanding.":[15],"According":[16],"to":[17,33,40,94,107],"their":[18],"respective":[19],"characteristics,":[20],"the":[21,41,45,53,59,84,96],"scheme":[22],"of":[23,55,58,86,118],"independently":[24],"designed":[25],"architecture":[26],"has":[27],"been":[28],"widely":[29],"used":[30],"correspondence":[32],"each":[34],"single":[35],"task.":[36],"This":[37],"may":[38],"lead":[39],"representation":[42],"learned":[43],"by":[44],"model":[46],"being":[47],"task-specific,":[48],"inevitably":[50],"result":[51],"lack":[54],"generalization":[56],"ability":[57],"feature":[60],"based":[61],"on":[62],"multi-modal":[63,97],"modeling.":[64],"More":[65],"recent":[66],"studies":[67],"shown":[69],"that":[70],"establishing":[71],"cross-modal":[72],"relationship":[73],"between":[74],"auditory":[75],"visual":[77],"stream":[78],"is":[79,105],"a":[80,92,102],"promising":[81],"solution":[82],"for":[83],"challenge":[85],"multi-task":[88],"learning.":[89],"Therefore,":[90],"as":[91],"motivation":[93],"bridge":[95],"associations":[98],"tasks,":[101],"unified":[103],"framework":[104],"proposed":[106],"achieve":[108],"target":[109],"with":[115],"joint":[116],"learning":[117],"modeling":[120],"this":[122],"study.":[123]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2022-05-05T00:00:00"}