{"id":"https://openalex.org/W4391021590","doi":"https://doi.org/10.1109/asru57964.2023.10389618","title":"Scenario-Aware Audio-Visual TF-Gridnet for Target Speech Extraction","display_name":"Scenario-Aware Audio-Visual TF-Gridnet for Target Speech Extraction","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021590","doi":"https://doi.org/10.1109/asru57964.2023.10389618"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]},{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","Tokyo Metropolitan University, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Tokyo, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois G. Germain","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035187454","display_name":"Sameer Khurana","orcid":"https://orcid.org/0000-0002-3182-1085"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Khurana","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001601327","display_name":"Chiori Hori","orcid":"https://orcid.org/0000-0002-4201-7578"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chiori Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2171,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89234864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9998999834060669,"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":0.9998000264167786,"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":0.8177329897880554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6378458142280579},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5000083446502686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3452848196029663},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1479887068271637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177329897880554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6378458142280579},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5000083446502686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3452848196029663},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1479887068271637}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389618","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":54,"referenced_works":["https://openalex.org/W2081144555","https://openalex.org/W2088079940","https://openalex.org/W2103104224","https://openalex.org/W2521686623","https://openalex.org/W2890964092","https://openalex.org/W2891205112","https://openalex.org/W2900292050","https://openalex.org/W2938646939","https://openalex.org/W2952218014","https://openalex.org/W2959214850","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2964283370","https://openalex.org/W2972568703","https://openalex.org/W2973062255","https://openalex.org/W2973231102","https://openalex.org/W3008400075","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/W3095082129","https://openalex.org/W3095379519","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3103434036","https://openalex.org/W3124666641","https://openalex.org/W3136499730","https://openalex.org/W3161480375","https://openalex.org/W3162475350","https://openalex.org/W3163287738","https://openalex.org/W3197832224","https://openalex.org/W4205689591","https://openalex.org/W4214698081","https://openalex.org/W4224920251","https://openalex.org/W4226062543","https://openalex.org/W4226338831","https://openalex.org/W4289665794","https://openalex.org/W4295308317","https://openalex.org/W4296070419","https://openalex.org/W4297632288","https://openalex.org/W4319862437","https://openalex.org/W4367597591","https://openalex.org/W4372271367","https://openalex.org/W4375869294","https://openalex.org/W4385822391","https://openalex.org/W6754420807","https://openalex.org/W6789284391","https://openalex.org/W6798523648","https://openalex.org/W6802983977","https://openalex.org/W6842816366","https://openalex.org/W6850377926"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519"],"abstract_inverted_index":{"Target":[0],"speech":[1,14,69],"extraction":[2,62],"aims":[3],"to":[4],"extract,":[5],"based":[6],"on":[7,109],"a":[8,12,44,53,57,80,94,121,127],"given":[9],"conditioning":[10,58],"cue,":[11],"target":[13,54],"signal":[15],"that":[16,47,83,101],"is":[17],"corrupted":[18],"by":[19,120],"interfering":[20,74,88],"sources,":[21,75],"such":[22],"as":[23,56,73],"noise":[24,71],"or":[25],"competing":[26],"speakers.":[27],"Building":[28],"upon":[29],"the":[30,33,49,61,65,85,110,137,140],"achievements":[31],"of":[32,52,87,136],"state-of-the-art":[34],"(SOTA)":[35],"time-frequency":[36],"speaker":[37,55],"separation":[38],"model":[39,82,97,105],"TF-GridNet,":[40],"we":[41,76],"propose":[42,78],"AV-GridNet,":[43],"visual-grounded":[45],"variant":[46],"incorporates":[48],"face":[50],"recording":[51],"factor":[59],"during":[60],"process.":[63],"Recognizing":[64],"inherent":[66],"dissimilarities":[67],"between":[68],"and":[70,91,125],"signals":[72],"also":[77,131],"SAV-GridNet,":[79],"scenario-aware":[81],"identifies":[84],"type":[86],"scenario":[89],"first":[90],"then":[92],"applies":[93],"dedicated":[95],"expert":[96],"trained":[98],"specifically":[99],"for":[100],"scenario.":[102],"Our":[103],"proposed":[104],"achieves":[106],"SOTA":[107],"results":[108,138],"second":[111],"COG-MHEAR":[112],"Audio-Visual":[113],"Speech":[114],"Enhancement":[115],"Challenge,":[116],"outperforming":[117],"other":[118],"models":[119],"significant":[122],"margin,":[123],"objectively":[124],"in":[126],"listening":[128],"test.":[129],"We":[130],"perform":[132],"an":[133],"extensive":[134],"analysis":[135],"under":[139],"two":[141],"scenarios.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}