{"id":"https://openalex.org/W4401609326","doi":"https://doi.org/10.1109/icasspw62465.2024.10626417","title":"SIR-Progressive Audio-Visual TF-Gridnet with ASR-Aware Selector for Target Speaker Extraction in MISP 2023 Challenge","display_name":"SIR-Progressive Audio-Visual TF-Gridnet with ASR-Aware Selector for Target Speaker Extraction in MISP 2023 Challenge","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609326","doi":"https://doi.org/10.1109/icasspw62465.2024.10626417"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626417","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626417","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 Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5038001536","display_name":"Zhongshu Hou","orcid":"https://orcid.org/0009-0000-5589-5372"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongshu Hou","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101737173","display_name":"Tianchi Sun","orcid":"https://orcid.org/0000-0002-4589-7769"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianchi Sun","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102994704","display_name":"Yuxiang Hu","orcid":"https://orcid.org/0009-0006-1546-5793"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Hu","raw_affiliation_strings":["Horizon Robotics,NJU-Horizon Intelligent Audio Lab,Beijing,China,100094"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,NJU-Horizon Intelligent Audio Lab,Beijing,China,100094","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030243018","display_name":"Changbao Zhu","orcid":"https://orcid.org/0000-0002-4438-8102"},"institutions":[{"id":"https://openalex.org/I4401726824","display_name":"Horizon Robotics (China)","ror":"https://ror.org/05cmv6g68","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726824"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changbao Zhu","raw_affiliation_strings":["Horizon Robotics,NJU-Horizon Intelligent Audio Lab,Beijing,China,100094"],"affiliations":[{"raw_affiliation_string":"Horizon Robotics,NJU-Horizon Intelligent Audio Lab,Beijing,China,100094","institution_ids":["https://openalex.org/I4401726824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437946","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-0164-1112"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059632088","display_name":"Jing L\u00fc","orcid":"https://orcid.org/0000-0001-9683-3768"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Lu","raw_affiliation_strings":["Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093"],"affiliations":[{"raw_affiliation_string":"Nanjing University,Key Laboratory of Modern Acoustics,Nanjing,China,210093","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038001536"],"corresponding_institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.6632,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74424616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9860000014305115,"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/computer-science","display_name":"Computer science","score":0.6822713613510132},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.49686768651008606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48375868797302246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37842297554016113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822713613510132},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.49686768651008606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48375868797302246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37842297554016113},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626417","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626417","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 Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2964283370","https://openalex.org/W3028077980","https://openalex.org/W3120336970","https://openalex.org/W4372271367","https://openalex.org/W4375869127","https://openalex.org/W4386561862","https://openalex.org/W4391021590","https://openalex.org/W4392902829","https://openalex.org/W6856619237"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"TF-GridNet":[0],"has":[1],"demonstrated":[2],"its":[3,15],"effectiveness":[4],"in":[5,94],"speech":[6,20,55,60],"separation":[7,49],"and":[8,29,91],"enhancement.":[9],"In":[10],"this":[11],"paper,":[12],"we":[13],"extend":[14],"capabilities":[16],"for":[17,52,71],"progressive":[18,31],"audio-visual":[19,26],"enhancement":[21,69],"by":[22],"introducing":[23],"an":[24],"attention-based":[25],"fusion":[27],"module":[28],"a":[30,45,79],"learning":[32],"strategy":[33],"based":[34,104],"on":[35,87],"the":[36,68,88,95],"signal-to-interference":[37],"ratio":[38],"(SIR).":[39],"The":[40,75],"model":[41],"is":[42,64],"integrated":[43],"with":[44],"prior":[46],"guided":[47],"source":[48],"(GSS)":[50],"process":[51],"robust":[53],"target":[54],"extraction.":[56],"A":[57],"subsequent":[58],"automatic":[59],"recognition":[61],"(ASR)-aware":[62],"selector":[63],"employed":[65],"to":[66],"choose":[67],"output":[70],"better":[72],"ASR":[73],"performance.":[74],"proposed":[76],"system":[77],"achieves":[78],"final":[80],"character":[81],"error":[82],"rate":[83],"(CER)":[84],"of":[85],"33.18%":[86],"evaluation":[89],"set":[90],"ranks":[92],"first":[93],"ICASSP":[96],"2024":[97],"Signal":[98],"Processing":[99,106],"Grand":[100],"Challenge:":[101],"Multimodal":[102],"Information":[103],"Speech":[105],"(MISP)":[107],"2023":[108],"Challenge.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}