{"id":"https://openalex.org/W4214698081","doi":"https://doi.org/10.1109/taslp.2022.3153258","title":"Selective Listening by Synchronizing Speech With Lips","display_name":"Selective Listening by Synchronizing Speech With Lips","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4214698081","doi":"https://doi.org/10.1109/taslp.2022.3153258"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3153258","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153258","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09721129.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09721129.pdf","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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Integrative Sciences and Engineering Programme, Institute of Data Science, National University of Singapore, Singapore","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8106-1176","affiliations":[{"raw_affiliation_string":"Integrative Sciences and Engineering Programme, Institute of Data Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, 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":[{"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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"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/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Kuaishou Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-1584-6282","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Kuaishou Technology, Shenzhen, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"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"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","DE","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","The Chinese University of Hong Kong, Shenzhen, China","University of Bremen, Bremen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"University of Bremen, Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9398,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94675292,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"1650","last_page":"1664"},"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":0.998199999332428,"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":0.9972000122070312,"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/speech-recognition","display_name":"Speech recognition","score":0.8025954365730286},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961414456367493},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5410991311073303},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.527839183807373},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5256627202033997},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5106635689735413},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5031012892723083},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4704051613807678},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4358682334423065},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3605574369430542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29453232884407043},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11285284161567688},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10724744200706482}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8025954365730286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961414456367493},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5410991311073303},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.527839183807373},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5256627202033997},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5106635689735413},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5031012892723083},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4704051613807678},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4358682334423065},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3605574369430542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29453232884407043},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11285284161567688},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10724744200706482},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3153258","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153258","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09721129.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2022.3153258","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3153258","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9657755/09721129.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2425286661","display_name":null,"funder_award_id":"EXC 2077","funder_id":"https://openalex.org/F4320324729","funder_display_name":"Universit\u00e4t Bremen"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320324729","display_name":"Universit\u00e4t Bremen","ror":"https://ror.org/04ers2y35"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4214698081.pdf"},"referenced_works_count":103,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1966823466","https://openalex.org/W1991139021","https://openalex.org/W2015143272","https://openalex.org/W2020141429","https://openalex.org/W2029199293","https://openalex.org/W2069681747","https://openalex.org/W2081144555","https://openalex.org/W2098717567","https://openalex.org/W2103104224","https://openalex.org/W2107938580","https://openalex.org/W2141411743","https://openalex.org/W2147455188","https://openalex.org/W2150769028","https://openalex.org/W2167709189","https://openalex.org/W2221409856","https://openalex.org/W2311038409","https://openalex.org/W2333091651","https://openalex.org/W2400006663","https://openalex.org/W2521686623","https://openalex.org/W2558649592","https://openalex.org/W2587150483","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2726515241","https://openalex.org/W2734774145","https://openalex.org/W2741151796","https://openalex.org/W2787692317","https://openalex.org/W2800022361","https://openalex.org/W2808631503","https://openalex.org/W2844030168","https://openalex.org/W2888968865","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2891833136","https://openalex.org/W2900292050","https://openalex.org/W2924115626","https://openalex.org/W2938646939","https://openalex.org/W2950864153","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2959214850","https://openalex.org/W2962788625","https://openalex.org/W2962960500","https://openalex.org/W2963082324","https://openalex.org/W2963103134","https://openalex.org/W2963528589","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2964283370","https://openalex.org/W2972460025","https://openalex.org/W2972513594","https://openalex.org/W2972568703","https://openalex.org/W2973054998","https://openalex.org/W2973062255","https://openalex.org/W3007376164","https://openalex.org/W3008003372","https://openalex.org/W3008400075","https://openalex.org/W3010457696","https://openalex.org/W3015199127","https://openalex.org/W3015445830","https://openalex.org/W3015623828","https://openalex.org/W3015636705","https://openalex.org/W3016361963","https://openalex.org/W3024147341","https://openalex.org/W3036438531","https://openalex.org/W3043140951","https://openalex.org/W3095082129","https://openalex.org/W3095379519","https://openalex.org/W3096214032","https://openalex.org/W3097653961","https://openalex.org/W3097741049","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3105928222","https://openalex.org/W3116298410","https://openalex.org/W3124666641","https://openalex.org/W3136499730","https://openalex.org/W3148386121","https://openalex.org/W3160672713","https://openalex.org/W3162475350","https://openalex.org/W3162534564","https://openalex.org/W3163287738","https://openalex.org/W3163573274","https://openalex.org/W3182657421","https://openalex.org/W3185109982","https://openalex.org/W3190394743","https://openalex.org/W3198234746","https://openalex.org/W3198575250","https://openalex.org/W3204420730","https://openalex.org/W3206008172","https://openalex.org/W3211358952","https://openalex.org/W3213412873","https://openalex.org/W4205654098","https://openalex.org/W4225682608","https://openalex.org/W4249654017","https://openalex.org/W4289665794","https://openalex.org/W6631190155","https://openalex.org/W6682948231","https://openalex.org/W6751512325","https://openalex.org/W6754420807","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"A":[0],"speaker":[1,12,72,126,151,159],"extraction":[2,152,160],"algorithm":[3],"seeks":[4],"to":[5,77,82,118,131,145],"extract":[6],"the":[7,24,57,65,71,79,87,93,97,120,139,142,146,150,157],"speech":[8,16,31,46,98],"of":[9,149,168],"a":[10,14,20,29,44,105,114],"target":[11,25,58,66,88,125],"from":[13,141],"multi-talker":[15],"mixture":[17],"when":[18,43],"given":[19],"cue":[21,123],"that":[22,74,92,156],"represents":[23],"speaker,":[26],"such":[27],"as":[28,70,78],"pre-enrolled":[30,45,60],"utterance,":[32],"or":[33],"an":[34,84],"accompanying":[35,101],"video":[36],"track.":[37],"Visual":[38],"cues":[39],"are":[40],"particularly":[41],"useful":[42],"is":[47,75,104],"not":[48],"available.":[49],"In":[50],"this":[51],"work,":[52],"we":[53,112],"don’t":[54],"rely":[55],"on":[56],"speaker’s":[59,67],"speech,":[61],"but":[62],"rather":[63],"use":[64],"face":[68],"track":[69],"cue,":[73],"referred":[76],"auxiliary":[80],"reference,":[81],"form":[83],"attractor":[85,147],"towards":[86],"speaker.":[89],"We":[90,137,154],"advocate":[91],"temporal":[94],"synchronization":[95,122],"between":[96],"and":[99,107,173],"its":[100],"lip":[102],"movements":[103],"direct":[106],"dominant":[108],"audio-visual":[109],"cue.":[110],"Therefore,":[111],"propose":[113],"self-supervised":[115],"pre-training":[116],"strategy,":[117],"exploit":[119],"speech-lip":[121],"for":[124],"extraction,":[127],"which":[128],"allows":[129],"us":[130],"leverage":[132],"abundant":[133],"unlabeled":[134],"in-domain":[135],"data.":[136],"transfer":[138],"knowledge":[140],"pre-trained":[143],"model":[144],"encoder":[148],"network.":[153],"show":[155],"proposed":[158],"network":[161],"outperforms":[162],"various":[163],"competitive":[164],"baselines":[165],"in":[166],"terms":[167],"signal":[169],"quality,":[170,172],"perceptual":[171],"intelligibility,":[174],"achieving":[175],"state-of-the-art":[176],"performance.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}