{"id":"https://openalex.org/W4389584625","doi":"https://doi.org/10.1109/lsp.2023.3341343","title":"IIFC-Net: A Monaural Speech Enhancement Network With High-Order Information Interaction and Feature Calibration","display_name":"IIFC-Net: A Monaural Speech Enhancement Network With High-Order Information Interaction and Feature Calibration","publication_year":2023,"publication_date":"2023-12-11","ids":{"openalex":"https://openalex.org/W4389584625","doi":"https://doi.org/10.1109/lsp.2023.3341343"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3341343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3341343","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/A5066989221","display_name":"Wenbing Wei","orcid":"https://orcid.org/0009-0008-7194-5198"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbing Wei","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0009-0008-7194-5198","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Hu","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0001-7505-1767","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University, Urumqi, China"],"raw_orcid":"https://orcid.org/0000-0001-6604-0951","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049944728","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-4076-7479"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of Electrical Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4076-7479","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2345,"currency":"USD","value_usd":2345},"apc_paid":null,"fwci":1.8089,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85226179,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"196","last_page":"200"},"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":0.9939000010490417,"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":0.9887999892234802,"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":0.7580184936523438},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.7403233051300049},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5079322457313538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48308661580085754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4439787268638611},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4128015339374542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3973141312599182},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3803851008415222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580184936523438},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.7403233051300049},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5079322457313538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48308661580085754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4439787268638611},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4128015339374542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3973141312599182},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3803851008415222},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3341343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3341343","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":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G3931585407","display_name":null,"funder_award_id":"U1903213","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2221409856","https://openalex.org/W2476548250","https://openalex.org/W2603567530","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2966269666","https://openalex.org/W2998161426","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3032514799","https://openalex.org/W3093712593","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3133834828","https://openalex.org/W3134695619","https://openalex.org/W3161950572","https://openalex.org/W3162493033","https://openalex.org/W3167976421","https://openalex.org/W3197627016","https://openalex.org/W3197729725","https://openalex.org/W3206809722","https://openalex.org/W3212231398","https://openalex.org/W4221143458","https://openalex.org/W4245919820","https://openalex.org/W4283803134","https://openalex.org/W4285504888","https://openalex.org/W4310059968","https://openalex.org/W4312095910","https://openalex.org/W4312443924","https://openalex.org/W4313174479","https://openalex.org/W4372259962","https://openalex.org/W6739901393","https://openalex.org/W6757632829","https://openalex.org/W6762114000","https://openalex.org/W6840866624","https://openalex.org/W6844662008"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2045506488","https://openalex.org/W1983045063","https://openalex.org/W4321794819","https://openalex.org/W2401567014","https://openalex.org/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Recently,":[0],"many":[1],"Transformer-style":[2],"dual-path":[3,72],"models":[4],"have":[5],"achieved":[6],"impressive":[7],"performance":[8,136],"for":[9],"speech":[10,30],"enhancement.":[11],"However,":[12],"their":[13,20],"high":[14],"parameters":[15],"and":[16,37,44,83,87,128,142],"computational":[17],"complexity":[18,38],"hinder":[19],"practical":[21],"application.":[22],"In":[23],"this":[24],"letter,":[25],"we":[26],"propose":[27],"a":[28,64,99,117],"monaural":[29],"enhancement":[31],"network":[32,49],"with":[33,56],"lower":[34],"parameter":[35],"count":[36],"based":[39],"on":[40,125],"high-order":[41,51,57],"information":[42,52,58,91],"interaction":[43,53,59],"feature":[45,100],"calibration":[46,101],"(IIFC-Net).":[47],"The":[48,120],"includes":[50],"Transformer":[54],"(HOIIFormer)":[55],"(HOII)":[60],"block":[61,103],"instead":[62],"of":[63,109,122,139],"multi-head":[65],"self-attention":[66],"(MHSA)":[67],"in":[68,137],"Transformer.":[69],"IIFC-Net":[70,133],"leverages":[71],"HOIIFormer":[73],"(DPH)":[74],"to":[75,104],"model":[76],"the":[77,93,106,126],"distant":[78],"dependency":[79],"relation":[80],"along":[81],"time":[82],"frequency":[84,107],"dimensions,":[85],"respectively,":[86],"effectively":[88],"captures":[89],"deep-level":[90],"through":[92],"HOII":[94],"block.":[95],"We":[96],"also":[97],"design":[98],"(FC)":[102],"enhance":[105],"components":[108],"target":[110],"speech,":[111],"which":[112],"can":[113],"be":[114],"verified":[115],"by":[116],"visualization":[118],"analysis.":[119],"outcomes":[121],"experiments":[123],"conducted":[124],"VoiceBank+DEMAND":[127],"WHAMR!":[129],"Datasets":[130],"demonstrate":[131],"that":[132],"achieves":[134],"comparable":[135],"terms":[138],"denoising,":[140],"dereverberation,":[141],"simultaneous":[143],"denoising":[144],"&":[145],"dereverberation.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}