{"id":"https://openalex.org/W4403126566","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693983","title":"Split-Attention Mechanisms with Graph Convolutional Network for Multi-Channel Speech Separation","display_name":"Split-Attention Mechanisms with Graph Convolutional Network for Multi-Channel Speech Separation","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126566","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693983"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10693983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10693983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5003356365","display_name":"YingWei Tan","orcid":"https://orcid.org/0000-0003-0944-118X"},"institutions":[{"id":"https://openalex.org/I8659980","display_name":"Volkswagen Group (United States)","ror":"https://ror.org/034e5n787","country_code":"US","type":"company","lineage":["https://openalex.org/I1319473763","https://openalex.org/I8659980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"YingWei Tan","raw_affiliation_strings":["Volkswagen-Mobvoi (Beijing) Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Volkswagen-Mobvoi (Beijing) Information Technology Co., Ltd","institution_ids":["https://openalex.org/I8659980"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843477","display_name":"Xue\u2010Feng Ding","orcid":"https://orcid.org/0000-0003-1076-0487"},"institutions":[{"id":"https://openalex.org/I8659980","display_name":"Volkswagen Group (United States)","ror":"https://ror.org/034e5n787","country_code":"US","type":"company","lineage":["https://openalex.org/I1319473763","https://openalex.org/I8659980"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"XueFeng Ding","raw_affiliation_strings":["Volkswagen-Mobvoi (Beijing) Information Technology Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Volkswagen-Mobvoi (Beijing) Information Technology Co., Ltd","institution_ids":["https://openalex.org/I8659980"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I8659980"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"140","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.933899998664856,"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":0.7514479756355286},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4572526812553406},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4308132529258728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37771281599998474},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.37459519505500793},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22694823145866394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12783008813858032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7514479756355286},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4572526812553406},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4308132529258728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37771281599998474},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.37459519505500793},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22694823145866394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12783008813858032}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10693983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10693983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2752782242","https://openalex.org/W2939360348","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W3015788098","https://openalex.org/W3016257794","https://openalex.org/W3016719260","https://openalex.org/W3032514799","https://openalex.org/W3095717210","https://openalex.org/W3163591408","https://openalex.org/W3171278394","https://openalex.org/W4225310539","https://openalex.org/W4297841846","https://openalex.org/W4372259962","https://openalex.org/W4375868849","https://openalex.org/W4375869047","https://openalex.org/W4385756463","https://openalex.org/W6726873649","https://openalex.org/W6762182681"],"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/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,38,80],"introduce":[4],"a":[5,10,40],"split-attention":[6],"mechanism":[7],"integrated":[8],"with":[9],"graph":[11,41],"convolutional":[12,42],"network":[13,43,74],"for":[14,109],"the":[15,25,59,85,94,102],"task":[16],"of":[17,28,62,97],"multi-channel":[18],"speech":[19,111],"separation.":[20],"Our":[21],"approach":[22,99],"involves":[23],"dividing":[24],"embedding":[26],"space":[27],"an":[29],"encoder-decoder":[30],"architecture":[31],"into":[32],"distinct":[33],"branches.":[34,75],"Within":[35],"each":[36],"branch,":[37],"employ":[39],"(GCN)":[44],"to":[45,57,101],"capture":[46],"spatial":[47],"dependencies":[48],"among":[49],"various":[50],"channels":[51],"(nodes).":[52],"This":[53],"framework":[54],"enables":[55],"us":[56],"harness":[58],"synergistic":[60],"benefits":[61],"both":[63],"feature-map":[64],"attention":[65,71],"and":[66],"multi-path":[67],"representation":[68],"by":[69],"channel-wise":[70],"across":[72],"diverse":[73],"To":[76],"validate":[77],"our":[78,98],"method,":[79],"conducted":[81],"extensive":[82],"experiments":[83],"on":[84],"spatialized":[86],"WSJ0-2MIX":[87],"dataset.":[88],"The":[89],"experimental":[90],"results":[91],"clearly":[92],"demonstrate":[93],"superior":[95],"performance":[96],"compared":[100],"baseline":[103],"Beam-Guided":[104],"TasNet,":[105],"indicating":[106],"its":[107],"potential":[108],"enhancing":[110],"separation":[112],"tasks.":[113]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}