{"id":"https://openalex.org/W4402715968","doi":"https://doi.org/10.1109/cis-ram61939.2024.10672879","title":"Listen to the Speaker in Your Gaze","display_name":"Listen to the Speaker in Your Gaze","publication_year":2024,"publication_date":"2024-08-08","ids":{"openalex":"https://openalex.org/W4402715968","doi":"https://doi.org/10.1109/cis-ram61939.2024.10672879"},"language":"en","primary_location":{"id":"doi:10.1109/cis-ram61939.2024.10672879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cis-ram61939.2024.10672879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM)","raw_type":"proceedings-article"},"type":"article","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/A5102793453","display_name":"Hongli Yang","orcid":"https://orcid.org/0009-0008-7605-655X"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongli Yang","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100457118","display_name":"Xinyi Chen","orcid":"https://orcid.org/0000-0003-3321-2483"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Chen","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367654","display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-4857-2214"},"institutions":[{"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088380372","display_name":"Siqi Cai","orcid":"https://orcid.org/0000-0003-3282-9246"},"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":"Siqi Cai","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"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/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Shenzhen Research Institute of Big Data,School of Data Science,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Research Institute of Big Data,School of Data Science,Shenzhen,China","institution_ids":["https://openalex.org/I4210099586"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102793453"],"corresponding_institution_ids":["https://openalex.org/I4210099586"],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56684692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9355999827384949,"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":0.9355999827384949,"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/gaze","display_name":"Gaze","score":0.7400208115577698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222458720207214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46363088488578796},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4132128357887268},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4115043580532074},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39387035369873047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37017738819122314},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32852819561958313}],"concepts":[{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.7400208115577698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222458720207214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46363088488578796},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4132128357887268},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4115043580532074},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39387035369873047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37017738819122314},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32852819561958313}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cis-ram61939.2024.10672879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cis-ram61939.2024.10672879","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Cybernetics and Intelligent Systems (CIS) and IEEE International Conference on Robotics, Automation and Mechatronics (RAM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1934410531","https://openalex.org/W2104396257","https://openalex.org/W2460742184","https://openalex.org/W2885976210","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W3007254760","https://openalex.org/W3099330747","https://openalex.org/W3137529719","https://openalex.org/W3162534564","https://openalex.org/W3183863723","https://openalex.org/W4205620265","https://openalex.org/W4214698081","https://openalex.org/W4243790825","https://openalex.org/W4285295776","https://openalex.org/W4362678363","https://openalex.org/W4367597591","https://openalex.org/W4372346854","https://openalex.org/W4377293287","https://openalex.org/W4380870136","https://openalex.org/W4383680008","https://openalex.org/W4385680760","https://openalex.org/W4386075783","https://openalex.org/W4386452375","https://openalex.org/W4392909318"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Attending":[0],"to":[1,50,68],"one\u2019s":[2],"voice":[3],"in":[4,116],"a":[5,20,80,100],"cocktail":[6],"party":[7],"is":[8,131],"notably":[9],"challenging,":[10],"particularly":[11],"for":[12],"individuals":[13],"with":[14,55],"hearing":[15],"impairments.":[16],"This":[17,59],"paper":[18],"proposes":[19],"novel":[21],"eye-controlled":[22],"target":[23,73,113],"speaker":[24],"extraction":[25],"system,":[26],"which":[27],"consists":[28],"of":[29,102,128],"an":[30],"eye-tracker,":[31],"face":[32,65,75,86],"detection":[33,66],"model,":[34],"Active":[35],"Speaker":[36,41],"Detection":[37],"(ASD),":[38],"and":[39,70,95,124],"Target":[40],"Extraction":[42],"(TSE)":[43],"model.":[44],"The":[45,104],"system":[46,92,109,130],"employs":[47],"the":[48,56,64,72,77,84,88,91,108,112],"eye-tracker":[49],"capture":[51],"real-time":[52,122],"video":[53,78],"together":[54],"listener\u2019s":[57],"gaze.":[58],"gaze":[60],"data":[61],"then":[62],"allows":[63],"model":[67],"locate":[69],"isolate":[71],"speaker\u2019s":[74,85,114],"within":[76],"on":[79,133],"frame-by-frame":[81],"basis.":[82],"Using":[83],"as":[87],"reference":[89],"cue,":[90],"can":[93],"discern":[94],"separate":[96],"his/her":[97],"speech":[98,115],"from":[99],"mixture":[101],"multi-talk.":[103],"experiments":[105],"show":[106],"that":[107],"effectively":[110],"extracts":[111],"complex":[117],"auditory":[118],"environments,":[119],"providing":[120],"both":[121],"performance":[123],"accuracy.":[125],"A":[126],"demonstration":[127],"our":[129,134],"available":[132],"website<sup":[135],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[136],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}