{"id":"https://openalex.org/W4403917834","doi":"https://doi.org/10.1109/taslp.2024.3488564","title":"DeFTAN-II: Efficient Multichannel Speech Enhancement With Subgroup Processing","display_name":"DeFTAN-II: Efficient Multichannel Speech Enhancement With Subgroup Processing","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403917834","doi":"https://doi.org/10.1109/taslp.2024.3488564"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3488564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3488564","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5003089552","display_name":"Dongheon Lee","orcid":"https://orcid.org/0000-0002-7667-2407"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongheon Lee","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7667-2407","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002212089","display_name":"Jung\u2010Woo Choi","orcid":"https://orcid.org/0000-0002-7264-6017"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-Woo Choi","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7264-6017","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.2523,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.8939763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"4850","last_page":"4866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9873999953269958,"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/T13289","display_name":"Infant Health and Development","score":0.944100022315979,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5207898020744324},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45792847871780396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42047828435897827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1884339153766632},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.04707193374633789}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5207898020744324},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45792847871780396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42047828435897827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1884339153766632},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.04707193374633789}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3488564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3488564","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G405343466","display_name":null,"funder_award_id":"RS-2024-00337945","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G7400092454","display_name":null,"funder_award_id":"RS-2024-00464269","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W2044893557","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2078528584","https://openalex.org/W2110485445","https://openalex.org/W2112796928","https://openalex.org/W2130722890","https://openalex.org/W2242685705","https://openalex.org/W2288645994","https://openalex.org/W2291877678","https://openalex.org/W2405774341","https://openalex.org/W2755891984","https://openalex.org/W2763188033","https://openalex.org/W2774389566","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963443859","https://openalex.org/W2963446712","https://openalex.org/W2963453742","https://openalex.org/W2963828919","https://openalex.org/W2964058413","https://openalex.org/W3015197852","https://openalex.org/W3015199127","https://openalex.org/W3015679215","https://openalex.org/W3015791598","https://openalex.org/W3032514799","https://openalex.org/W3042857426","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3097906045","https://openalex.org/W3134695619","https://openalex.org/W3138516171","https://openalex.org/W3163652268","https://openalex.org/W3177067699","https://openalex.org/W3196940724","https://openalex.org/W3198100319","https://openalex.org/W3198511309","https://openalex.org/W3205004157","https://openalex.org/W3206809722","https://openalex.org/W3209472002","https://openalex.org/W4205689591","https://openalex.org/W4221165117","https://openalex.org/W4224919782","https://openalex.org/W4224932531","https://openalex.org/W4224936432","https://openalex.org/W4225270933","https://openalex.org/W4225310539","https://openalex.org/W4283794752","https://openalex.org/W4296068774","https://openalex.org/W4306802258","https://openalex.org/W4312219134","https://openalex.org/W4312701366","https://openalex.org/W4312950730","https://openalex.org/W4321608474","https://openalex.org/W4372267870","https://openalex.org/W4385245566","https://openalex.org/W4385756463","https://openalex.org/W4385823109","https://openalex.org/W4386075553","https://openalex.org/W4388755868","https://openalex.org/W6631190155","https://openalex.org/W6731370813","https://openalex.org/W6764679822","https://openalex.org/W6771571646","https://openalex.org/W6780218876","https://openalex.org/W6793164127","https://openalex.org/W6797761920"],"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/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"In":[0,78],"this":[1],"work,":[2],"we":[3,47,118,161,177],"present":[4],"DeFTAN-II,":[5],"an":[6],"efficient":[7],"multichannel":[8,157],"speech":[9,25,158],"enhancement":[10,159],"model":[11],"based":[12],"on":[13,183],"transformer":[14],"architecture":[15],"and":[16,39,94,105,111,115,129],"subgroup":[17,49,67,166],"processing.":[18],"Despite":[19],"the":[20,35,75,79,102,109,143,179],"success":[21],"of":[22,56,74,89,142,145],"transformers":[23],"in":[24,30,51,71,140,193],"enhancement,":[26],"they":[27],"face":[28],"challenges":[29],"capturing":[31],"local":[32,146],"relations,":[33,117],"reducing":[34],"high":[36],"computational":[37,103,174],"complexity,":[38],"lowering":[40],"memory":[41,106],"usage.":[42,107],"To":[43],"address":[44],"these":[45],"limitations,":[46],"introduce":[48,119],"processing":[50,68,167],"our":[52],"model,":[53],"combining":[54],"subgroups":[55,62,90,122],"locally":[57,127],"emphasized":[58,128],"features":[59,139,147],"with":[60,155,165],"other":[61],"containing":[63],"original":[64],"features.":[65,131],"The":[66,132],"is":[69,91],"implemented":[70],"several":[72],"blocks":[73,83],"proposed":[76,80],"network.":[77],"split":[81],"dense":[82],"extracting":[84,113],"spatial":[85],"features,":[86],"a":[87],"pair":[88],"sequentially":[92],"concatenated":[93],"processed":[95,148],"by":[96,149],"convolution":[97],"layers":[98],"to":[99,123],"effectively":[100],"reduce":[101],"complexity":[104],"For":[108],"F-":[110],"T-transformers":[112],"temporal":[114],"spectral":[116],"cross-attention":[120],"between":[121,126],"identify":[124],"relationships":[125],"non-emphasized":[130],"dual-path":[133],"feedforward":[134],"network":[135],"then":[136],"aggregates":[137],"attended":[138],"terms":[141],"gating":[144],"dilated":[150],"convolutions.":[151],"Through":[152],"extensive":[153],"comparisons":[154],"state-of-the-art":[156],"models,":[160],"demonstrate":[162],"that":[163],"DeFTAN-II":[164],"outperforms":[168],"existing":[169],"methods":[170],"at":[171],"significantly":[172],"lower":[173],"complexity.":[175],"Moreover,":[176],"evaluate":[178],"model's":[180],"generalization":[181],"capability":[182],"real-world":[184],"data":[185],"without":[186],"fine-tuning,":[187],"which":[188],"further":[189],"demonstrates":[190],"its":[191],"effectiveness":[192],"practical":[194],"scenarios.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}