{"id":"https://openalex.org/W4375869294","doi":"https://doi.org/10.1109/icassp49357.2023.10097232","title":"ImagineNet: Target Speaker Extraction with Intermittent Visual Cue Through Embedding Inpainting","display_name":"ImagineNet: Target Speaker Extraction with Intermittent Visual Cue Through Embedding Inpainting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869294","doi":"https://doi.org/10.1109/icassp49357.2023.10097232"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["National University of Singapore (NUS),Institute of Data Science,Singapore","Department of Electrical and Computer Engineering, NUS, Singapore","Institute of Data Science, National University of Singapore (NUS), Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore (NUS),Institute of Data Science,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, NUS, Singapore","institution_ids":[]},{"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/A5006131727","display_name":"Wupeng Wang","orcid":"https://orcid.org/0009-0000-5360-2054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wupeng Wang","raw_affiliation_strings":["NUS,Department of Electrical and Computer Engineering,Singapore","Department of Electrical and Computer Engineering, NUS, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NUS,Department of Electrical and Computer Engineering,Singapore","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, NUS, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027146195","display_name":"Marvin Borsdorf","orcid":"https://orcid.org/0000-0003-1769-1621"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Marvin Borsdorf","raw_affiliation_strings":["University of Bremen,Machine Listening Lab,Germany","Machine Listening Lab, University of Bremen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bremen,Machine Listening Lab,Germany","institution_ids":["https://openalex.org/I180437899"]},{"raw_affiliation_string":"Machine Listening Lab, University of Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]}]},{"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/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/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"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"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data, School of Data Science,Shenzhen,China","Department of Electrical and Computer Engineering, NUS, Singapore","Machine Listening Lab, University of Bremen, Germany","Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Shenzhen Research Institute of Big Data, School of Data Science,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, NUS, Singapore","institution_ids":[]},{"raw_affiliation_string":"Machine Listening Lab, University of Bremen, Germany","institution_ids":["https://openalex.org/I180437899"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9998000264167786,"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":0.9965000152587891,"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":0.7915705442428589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6513654589653015},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6001814603805542},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.5865300297737122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5656994581222534},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5187147259712219},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4480837881565094},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.447482705116272},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4271330237388611},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13379636406898499},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08086764812469482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7915705442428589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6513654589653015},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6001814603805542},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5865300297737122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656994581222534},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5187147259712219},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4480837881565094},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.447482705116272},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4271330237388611},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13379636406898499},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08086764812469482},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322170","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2221409856","https://openalex.org/W2808631503","https://openalex.org/W2898371500","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2964171275","https://openalex.org/W2972513594","https://openalex.org/W2973062255","https://openalex.org/W2992838650","https://openalex.org/W3008400075","https://openalex.org/W3015791137","https://openalex.org/W3016361963","https://openalex.org/W3035524453","https://openalex.org/W3095379519","https://openalex.org/W3097450720","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3105183525","https://openalex.org/W3105938520","https://openalex.org/W3160658686","https://openalex.org/W3161904430","https://openalex.org/W3162475350","https://openalex.org/W3163287738","https://openalex.org/W3198575250","https://openalex.org/W3201844719","https://openalex.org/W3206008172","https://openalex.org/W3210390090","https://openalex.org/W4214698081","https://openalex.org/W4224917445","https://openalex.org/W4224920251","https://openalex.org/W4226062543","https://openalex.org/W4226338831","https://openalex.org/W4285819380","https://openalex.org/W4289665794","https://openalex.org/W4295308317","https://openalex.org/W4296070419","https://openalex.org/W4297632288","https://openalex.org/W4297808394","https://openalex.org/W4319663835","https://openalex.org/W6640963894","https://openalex.org/W6755462816","https://openalex.org/W6769644785","https://openalex.org/W6790096238","https://openalex.org/W6842816366","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W4242046654","https://openalex.org/W1504109132","https://openalex.org/W3134074939","https://openalex.org/W2117562399","https://openalex.org/W3174923100","https://openalex.org/W2244018504","https://openalex.org/W3134175397","https://openalex.org/W4307784074"],"abstract_inverted_index":{"The":[0,55,171],"speaker":[1,13,29,107,118],"extraction":[2,108,119],"technique":[3],"seeks":[4],"to":[5,32,68,79,125],"single":[6],"out":[7],"the":[8,15,27,52,105,127,132,135,178],"voice":[9],"of":[10,26,57,154,166,182],"a":[11,19,37,41,46,116],"target":[12,28],"from":[14],"interfering":[16],"voices":[17],"in":[18,45,89,180],"speech":[20],"mixture.":[21],"Typically":[22],"an":[23,143],"auxiliary":[24,53],"reference":[25],"is":[30,60,77,86],"used":[31,168],"form":[33],"voluntary":[34],"attention.":[35],"Either":[36],"pre-recorded":[38],"utterance":[39],"or":[40,95],"synchronized":[42],"lip":[43],"movement":[44],"video":[47],"clip":[48],"can":[49,98],"serve":[50],"as":[51],"reference.":[54],"use":[56],"visual":[58,84,93,112,121,155,169],"cue":[59,85],"not":[61],"only":[62],"feasible,":[63],"but":[64],"also":[65,150],"effective":[66],"due":[67],"its":[69],"noise":[70],"robustness,":[71],"and":[72,120,146,158,187],"becoming":[73],"popular.":[74],"However,":[75],"it":[76],"difficult":[78],"guarantee":[80],"that":[81,175],"such":[82],"parallel":[83],"always":[87],"available":[88],"real-world":[90],"applications":[91],"where":[92],"occlusion":[94],"intermittent":[96,111],"communication":[97],"occur.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103,176],"study":[104,159],"audio-visual":[106],"algorithms":[109],"with":[110,142,163],"cue.":[113],"We":[114,149],"propose":[115,151],"joint":[117],"embedding":[122],"inpainting":[123,156],"framework":[124],"explore":[126],"mutual":[128],"benefits.":[129],"To":[130],"encourage":[131],"interaction":[133],"between":[134],"two":[136,152,164],"tasks,":[137],"they":[138],"are":[139],"performed":[140],"alternately":[141],"interlacing":[144],"structure":[145],"optimized":[147],"jointly.":[148],"types":[153,165],"losses":[157],"our":[160],"proposed":[161],"method":[162],"popularly":[167],"embeddings.":[170],"experimental":[172],"results":[173],"show":[174],"outperform":[177],"baseline":[179],"terms":[181],"signal":[183],"quality,":[184,186],"perceptual":[185],"intelligibility.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}