{"id":"https://openalex.org/W4408345572","doi":"https://doi.org/10.1109/icassp49660.2025.10888193","title":"Co-Attention Based Multi-Channel TF-GridNet for Speech Separation with Ad-Hoc Microphone Arrays","display_name":"Co-Attention Based Multi-Channel TF-GridNet for Speech Separation with Ad-Hoc Microphone Arrays","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345572","doi":"https://doi.org/10.1109/icassp49660.2025.10888193"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888193","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/A5101542472","display_name":"Hongmei Guo","orcid":"https://orcid.org/0000-0003-4082-7363"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongmei Guo","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032679393","display_name":"Linfeng Feng","orcid":"https://orcid.org/0009-0008-7908-779X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linfeng Feng","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101436487","display_name":"Yijiang Chen","orcid":"https://orcid.org/0000-0002-3224-4339"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijiang Chen","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764668","display_name":"Xueqing Li","orcid":"https://orcid.org/0000-0001-8844-6119"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqing Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111344231","display_name":"Boyu Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Zhu","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100427209","display_name":"Haoyu Wang","orcid":"https://orcid.org/0000-0003-4478-0363"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao-Yu Wang","raw_affiliation_strings":["Southern University of Science and Technology,School of Systems Engineering and Intelligent Manufacturing,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,School of Systems Engineering and Intelligent Manufacturing,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100740143","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0002-0019-4197"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9947999715805054,"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":0.9915000200271606,"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":0.6468855142593384},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5848242044448853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5748721957206726},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4962158799171448},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.47517815232276917},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42472514510154724},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1666681468486786},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1425749957561493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07495656609535217}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6468855142593384},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5848242044448853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5748721957206726},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4962158799171448},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.47517815232276917},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42472514510154724},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1666681468486786},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1425749957561493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07495656609535217},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888193","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":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W2148613904","https://openalex.org/W2898268964","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W3015372568","https://openalex.org/W3015791598","https://openalex.org/W3016094953","https://openalex.org/W3086578443","https://openalex.org/W3106603336","https://openalex.org/W3132229649","https://openalex.org/W3171278394","https://openalex.org/W4221158617","https://openalex.org/W4293162951","https://openalex.org/W4294891356","https://openalex.org/W4312806213","https://openalex.org/W4372271367","https://openalex.org/W4372347014","https://openalex.org/W4375869206","https://openalex.org/W4385822396","https://openalex.org/W4385823020","https://openalex.org/W4390872461","https://openalex.org/W4391621214","https://openalex.org/W4392904014","https://openalex.org/W4392910821","https://openalex.org/W4395471098","https://openalex.org/W4400975497","https://openalex.org/W4407449947","https://openalex.org/W6766380642"],"related_works":["https://openalex.org/W107154053","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2791440692","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2149163000"],"abstract_inverted_index":{"Speech":[0],"separation":[1,60,126],"using":[2],"ad-hoc":[3,62],"microphone":[4,63],"arrays":[5],"has":[6],"been":[7],"explored,":[8],"but":[9],"there":[10],"is":[11,30,68,94],"still":[12],"significant":[13],"room":[14],"for":[15,58,101,124],"improvement,":[16],"especially":[17],"in":[18,33,120,127],"complex":[19],"scenarios":[20],"with":[21,61],"varying":[22],"channel":[23,85,122],"conditions.":[24],"Co-attention,":[25],"a":[26,54],"feature":[27],"fusion":[28,35,123],"mechanism,":[29],"widely":[31],"used":[32],"multimodal":[34],"to":[36,73,98],"capture":[37],"the":[38,44,71,75,88,95,108,116],"cooperation":[39],"between":[40,77],"modalities":[41],"and":[42],"enhance":[43,74],"representation":[45],"of":[46,90,118],"extracted":[47],"features.":[48],"In":[49],"this":[50,93],"paper,":[51],"we":[52],"propose":[53],"co-attention-based":[55],"multi-channel":[56],"model":[57,72],"speech":[59,102,125],"arrays.":[64],"The":[65],"co-attention":[66,100,119],"mechanism":[67],"integrated":[69],"into":[70],"interaction":[76],"different":[78],"speakers":[79],"across":[80],"multiple":[81],"channels,":[82],"enabling":[83],"efficient":[84],"fusion.":[86],"To":[87],"best":[89],"our":[91],"knowledge,":[92],"first":[96],"work":[97],"apply":[99],"separation.":[103],"Experimental":[104],"results":[105],"demonstrate":[106],"that":[107],"proposed":[109],"method":[110],"significantly":[111],"outperforms":[112],"existing":[113],"approaches,":[114],"underscoring":[115],"importance":[117],"optimizing":[121],"challenging":[128],"acoustic":[129],"environments.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
