{"id":"https://openalex.org/W4321608474","doi":"https://doi.org/10.1109/lsp.2023.3244428","title":"DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel Speech Enhancement","display_name":"DeFT-AN: Dense Frequency-Time Attentive Network for Multichannel Speech Enhancement","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321608474","doi":"https://doi.org/10.1109/lsp.2023.3244428"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3244428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3244428","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7667-2407","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, 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":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7264-6017","affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, 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":6.9589,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97955641,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"155","last_page":"159"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.996999979019165,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7355766892433167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6728183031082153},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.6210607290267944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5879865288734436},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4573367238044739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30133455991744995},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1806822121143341},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.14012247323989868}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7355766892433167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6728183031082153},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.6210607290267944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5879865288734436},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4573367238044739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30133455991744995},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1806822121143341},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.14012247323989868},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3244428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3244428","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G1654580039","display_name":null,"funder_award_id":"CRC21011","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320325370","display_name":"National Research Council of Science and Technology","ror":"https://ror.org/058rymf81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W2067295501","https://openalex.org/W2110485445","https://openalex.org/W2125114513","https://openalex.org/W2130722890","https://openalex.org/W2141411743","https://openalex.org/W2242685705","https://openalex.org/W2516001803","https://openalex.org/W2550143307","https://openalex.org/W2899663614","https://openalex.org/W2943554574","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963443859","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3015791598","https://openalex.org/W3049430014","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3161950572","https://openalex.org/W3163652268","https://openalex.org/W3177067699","https://openalex.org/W3205004157","https://openalex.org/W3209472002","https://openalex.org/W4224919782","https://openalex.org/W4224936432","https://openalex.org/W4296068418","https://openalex.org/W4372271367","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6755977528"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2981428355","https://openalex.org/W1834994814"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"propose":[4],"a":[5,17,23,68,72,77],"dense":[6,87],"frequency-time":[7],"attentive":[8],"network":[9,20,49,75],"(DeFT-AN)":[10],"for":[11,28,56,133],"multichannel":[12,116],"speech":[13,134],"enhancement.":[14],"DeFT-AN":[15,113],"is":[16,118],"mask":[18,47],"estimation":[19,48],"that":[21],"predicts":[22],"complex":[24],"spectral":[25,69],"masking":[26],"pattern":[27],"suppressing":[29],"the":[30,36,60,93],"noise":[31],"and":[32,63,76,89,106,125,136],"reverberation":[33],"embedded":[34],"in":[35,59,104,128],"short-time":[37],"Fourier":[38],"transform":[39],"(STFT)":[40],"of":[41,54,86,97,112,130],"an":[42],"input":[43],"signal.":[44],"The":[45,84,109],"proposed":[46],"incorporates":[50],"three":[51,94],"different":[52,95],"types":[53],"blocks":[55,88],"aggregating":[57],"information":[58],"spatial,":[61],"spectral,":[62],"temporal":[64,78],"dimensions.":[65],"It":[66],"utilizes":[67],"transformer":[70],"with":[71,80],"modified":[73],"feed-forward":[74],"conformer":[79],"sequential":[81],"dilated":[82],"convolutions.":[83],"use":[85],"transformers":[90],"dedicated":[91],"to":[92],"characteristics":[96],"audio":[98],"signals":[99],"enables":[100],"more":[101],"comprehensive":[102],"enhancement":[103],"noisy":[105,124],"reverberant":[107,126],"environments.":[108],"remarkable":[110],"performance":[111],"over":[114],"state-of-the-art":[115],"models":[117],"demonstrated":[119],"based":[120],"on":[121],"two":[122],"popular":[123],"datasets":[127],"terms":[129],"various":[131],"metrics":[132],"quality":[135],"intelligibility.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":15}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}