{"id":"https://openalex.org/W3163287738","doi":"https://doi.org/10.1109/icassp39728.2021.9414023","title":"Muse: Multi-Modal Target Speaker Extraction with Visual Cues","display_name":"Muse: Multi-Modal Target Speaker Extraction with Visual Cues","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163287738","doi":"https://doi.org/10.1109/icassp39728.2021.9414023","mag":"3163287738"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210126319","display_name":"Duke-NUS Medical School","ror":"https://ror.org/02j1m6098","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596","https://openalex.org/I170897317","https://openalex.org/I4210126319"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Graduate School for Integrative Sciences and Engineering, NUS, Singapore","Institute of Data Science, National University of Singapore (NUS), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School for Integrative Sciences and Engineering, NUS, Singapore","institution_ids":["https://openalex.org/I4210126319"]},{"raw_affiliation_string":"Institute of Data Science, National University of Singapore (NUS), Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["NUS, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUS, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["NUS, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUS, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I180437899","display_name":"University of Bremen","ror":"https://ror.org/04ers2y35","country_code":"DE","type":"education","lineage":["https://openalex.org/I180437899"]}],"countries":["DE","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute of Data Science, National University of Singapore (NUS), Singapore","Machine Listening Lab, University of Bremen, Germany","NUS, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Data Science, National University of Singapore (NUS), Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Machine Listening Lab, University of Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]},{"raw_affiliation_string":"NUS, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7975,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.97664778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6678","last_page":"6682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.7950887680053711},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7464203238487244},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6177486777305603},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5712329149246216},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.5199702978134155},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5032264590263367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4942891597747803},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46186500787734985},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.43966278433799744},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4181097745895386},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4120141565799713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3554536700248718},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.2717774510383606},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.09431526064872742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950887680053711},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7464203238487244},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6177486777305603},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5712329149246216},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.5199702978134155},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5032264590263367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4942891597747803},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46186500787734985},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.43966278433799744},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4181097745895386},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4120141565799713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3554536700248718},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.2717774510383606},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.09431526064872742},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2015143272","https://openalex.org/W2020141429","https://openalex.org/W2029199293","https://openalex.org/W2123157731","https://openalex.org/W2150415460","https://openalex.org/W2221409856","https://openalex.org/W2800022361","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2952218014","https://openalex.org/W2962960500","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W2973062255","https://openalex.org/W3000647100","https://openalex.org/W3008400075","https://openalex.org/W3015623828","https://openalex.org/W3016098309","https://openalex.org/W3016361963","https://openalex.org/W3024147341","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3124666641","https://openalex.org/W4289665794","https://openalex.org/W6688843265","https://openalex.org/W6750885114","https://openalex.org/W6754392867","https://openalex.org/W6754420807","https://openalex.org/W6757716108","https://openalex.org/W6776505702","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W1999004162","https://openalex.org/W4280634406","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speaker":[0],"extraction":[1,83],"algorithm":[2],"relies":[3],"on":[4,91],"the":[5,9,13,28,31,72],"speech":[6,23,35,63,67],"sample":[7],"from":[8,65],"target":[10,62],"speaker":[11,82],"as":[12,41],"reference":[14,22,61,76],"point":[15],"to":[16,54,59],"focus":[17],"its":[18],"attention.":[19],"Such":[20],"a":[21,51,80,92],"is":[24,88],"typically":[25],"pre-recorded.":[26],"On":[27],"other":[29,100],"hand,":[30],"temporal":[32],"synchronization":[33],"between":[34],"and":[36,107],"lip":[37,93],"movement":[38],"also":[39,110],"serves":[40],"an":[42],"informative":[43],"cue.":[44],"Motivated":[45],"by":[46],"this":[47],"idea,":[48],"we":[49],"study":[50],"novel":[52],"technique":[53],"use":[55],"speech-lip":[56],"visual":[57],"cues":[58],"extract":[60],"directly":[64],"mixture":[66],"during":[68],"inference":[69],"time,":[70],"without":[71],"need":[73],"of":[74,105],"pre-recorded":[75],"speech.":[77],"We":[78],"propose":[79],"multi-modal":[81],"network,":[84],"named":[85],"MuSE,":[86],"that":[87],"conditioned":[89],"only":[90,98],"image":[94],"sequence.":[95],"MuSE":[96],"not":[97],"outperforms":[99],"competitive":[101],"baselines":[102],"in":[103,114],"terms":[104],"SI-SDR":[106],"PESQ,":[108],"but":[109],"shows":[111],"consistent":[112],"improvement":[113],"cross-dataset":[115],"evaluations.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}