{"id":"https://openalex.org/W4408355304","doi":"https://doi.org/10.1109/icassp49660.2025.10887655","title":"Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction","display_name":"Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355304","doi":"https://doi.org/10.1109/icassp49660.2025.10887655"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5100343643","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0003-4882-0959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["Meta AI,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013092421","display_name":"Rodrigo Mira","orcid":"https://orcid.org/0000-0002-9493-3842"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rodrigo Mira","raw_affiliation_strings":["Imperial College,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081576515","display_name":"Honglie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honglie Chen","raw_affiliation_strings":["Meta AI,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Meta AI,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Meta AI,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79181198,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9764000177383423,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9764000177383423,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9144999980926514,"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":0.7484948635101318},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6593706607818604},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5586564540863037},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5034465193748474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40390297770500183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484948635101318},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6593706607818604},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5586564540863037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5034465193748474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40390297770500183},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/icassp49660.2025.10887655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1991139021","https://openalex.org/W2127851351","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2799473636","https://openalex.org/W2891833136","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W3011424113","https://openalex.org/W3015199127","https://openalex.org/W3015225820","https://openalex.org/W3015306128","https://openalex.org/W3015636705","https://openalex.org/W3024869864","https://openalex.org/W3096893582","https://openalex.org/W3097450720","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3185109982","https://openalex.org/W4210710538","https://openalex.org/W4224918929","https://openalex.org/W4232282348","https://openalex.org/W4288054834","https://openalex.org/W4293363567","https://openalex.org/W4296069305","https://openalex.org/W4297841411","https://openalex.org/W4312711418","https://openalex.org/W4367597591","https://openalex.org/W4372260127","https://openalex.org/W4372260474","https://openalex.org/W4372271367","https://openalex.org/W4372346152","https://openalex.org/W4386071467","https://openalex.org/W4402112611","https://openalex.org/W6726497184","https://openalex.org/W6745297980","https://openalex.org/W6757817989","https://openalex.org/W6811340617","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6852997429","https://openalex.org/W6857534457"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1,27],"paper,":[2],"we":[3,113,144,159],"investigate":[4],"a":[5,66],"novel":[6],"approach":[7,76],"for":[8,178],"Target":[9],"Speech":[10,31],"Extraction":[11,32],"(TSE),":[12],"which":[13],"relies":[14,120],"solely":[15],"on":[16,40,107,122],"textual":[17,91,150],"context":[18,151],"to":[19,26,56,169],"extract":[20],"the":[21,46,58,118,133],"target":[22,47,59,135],"speech.":[23],"We":[24,98],"refer":[25],"task":[28],"as":[29,155],"Contextual":[30],"(CSE).":[33],"Unlike":[34],"traditional":[35],"TSE":[36],"methods":[37],"that":[38,93,115,146],"rely":[39],"pre-recorded":[41],"enrollment":[42,153],"utterances,":[43],"video":[44],"of":[45,69],"speaker\u2019s":[48],"face,":[49],"spatial":[50],"information,":[51],"or":[52,175],"other":[53],"explicit":[54],"cues":[55,156],"identify":[57],"stream,":[60],"our":[61,111,162],"proposed":[62],"method":[63],"requires":[64],"only":[65,138],"few":[67],"turns":[68],"previous":[70,140],"dialogue":[71,92,123,141],"(or":[72],"monologue)":[73],"history.":[74],"This":[75],"is":[77],"naturally":[78],"feasible":[79],"in":[80,131],"mobile":[81],"messaging":[82],"environments":[83],"where":[84],"voice":[85],"recordings":[86],"are":[87],"typically":[88],"preceded":[89],"by":[90,147],"can":[94,126],"be":[95],"leveraged":[96],"implicitly.":[97],"present":[99],"three":[100,108],"CSE":[101],"models":[102],"and":[103,152,165],"analyze":[104],"their":[105],"performances":[106],"datasets.":[109],"Through":[110],"experiments,":[112],"demonstrate":[114],"even":[116],"when":[117],"model":[119],"purely":[121],"history,":[124],"it":[125],"achieve":[127],"over":[128],"90%":[129],"accuracy":[130],"identifying":[132],"correct":[134],"stream":[136],"with":[137],"two":[139],"turns.":[142],"Furthermore,":[143],"show":[145],"leveraging":[148],"both":[149,177],"utterances":[154],"during":[157,173],"training,":[158],"further":[160],"enhance":[161],"model\u2019s":[163],"flexibility":[164],"effectiveness,":[166],"allowing":[167],"us":[168],"use":[170],"either":[171],"cue":[172],"inference,":[174],"combine":[176],"improved":[179],"performance.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}