{"id":"https://openalex.org/W4396542462","doi":"https://doi.org/10.1109/taslp.2024.3395978","title":"Residual Fusion Probabilistic Knowledge Distillation for Speech Enhancement","display_name":"Residual Fusion Probabilistic Knowledge Distillation for Speech Enhancement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396542462","doi":"https://doi.org/10.1109/taslp.2024.3395978"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3395978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3395978","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/A5008143740","display_name":"Jiaming Cheng","orcid":"https://orcid.org/0000-0002-7136-7876"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Cheng","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China","School of Information Science and Engineering, Southeast University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-7136-7876","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089624396","display_name":"Ruiyu Liang","orcid":"https://orcid.org/0000-0002-6813-4203"},"institutions":[{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiyu Liang","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China","School of Information Science and Engineering, Southeast University, Nanjing, P. R. China","School of Communication Engineering, Nanjing Institute of Technology, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-6813-4203","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Communication Engineering, Nanjing Institute of Technology, Nanjing, P. R. China","institution_ids":["https://openalex.org/I2799736854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048143843","display_name":"Lin Zhou","orcid":"https://orcid.org/0000-0003-4810-6704"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Zhou","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China","School of Information Science and Engineering, Southeast University, Nanjing, P. R. China"],"raw_orcid":"https://orcid.org/0000-0003-4810-6704","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101872701","display_name":"Li Zhao","orcid":"https://orcid.org/0000-0002-7145-4718"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhao","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University, Nanjing, China","School of Information Science and Engineering, Southeast University, Nanjing, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University, Nanjing, P. R. China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108049798","display_name":"Chengwei Huang","orcid":"https://orcid.org/0000-0001-9060-6361"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Huang","raw_affiliation_strings":["Zhejiang Laboratory, Hangzhou, China","Zhejiang Laboratory, Hangzhou, P. R. China"],"raw_orcid":"https://orcid.org/0000-0001-9060-6361","affiliations":[{"raw_affiliation_string":"Zhejiang Laboratory, Hangzhou, China","institution_ids":["https://openalex.org/I4210123185"]},{"raw_affiliation_string":"Zhejiang Laboratory, Hangzhou, P. R. China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6478-8699","affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6458,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62492308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"32","issue":null,"first_page":"2680","last_page":"2691"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7521777153015137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7475507855415344},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6585528254508972},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5644002556800842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5631848573684692},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4986693859100342},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.4951404631137848},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4655535817146301},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45786526799201965},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4534764587879181},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4392821788787842},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21224382519721985}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7521777153015137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7475507855415344},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6585528254508972},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5644002556800842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5631848573684692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4986693859100342},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.4951404631137848},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4655535817146301},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45786526799201965},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4534764587879181},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4392821788787842},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21224382519721985},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3395978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3395978","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"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1773051","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1773051","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G174787991","display_name":null,"funder_award_id":"62001215","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":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1888374534","https://openalex.org/W2119913432","https://openalex.org/W2124509324","https://openalex.org/W2126942983","https://openalex.org/W2171850596","https://openalex.org/W2398042854","https://openalex.org/W2516001803","https://openalex.org/W2792764867","https://openalex.org/W2962866211","https://openalex.org/W2963045393","https://openalex.org/W2963122961","https://openalex.org/W2963868408","https://openalex.org/W2964058413","https://openalex.org/W2971417062","https://openalex.org/W2972592847","https://openalex.org/W3030901202","https://openalex.org/W3031505850","https://openalex.org/W3036367741","https://openalex.org/W3046667470","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3097312999","https://openalex.org/W3147539069","https://openalex.org/W3156828761","https://openalex.org/W3160085755","https://openalex.org/W3162493033","https://openalex.org/W3162538144","https://openalex.org/W3163341049","https://openalex.org/W3177196641","https://openalex.org/W3196940724","https://openalex.org/W4205689591","https://openalex.org/W4210402803","https://openalex.org/W4221143458","https://openalex.org/W4221149546","https://openalex.org/W4224917453","https://openalex.org/W4225270933","https://openalex.org/W4226185896","https://openalex.org/W4285133995","https://openalex.org/W4296068808","https://openalex.org/W4372347447","https://openalex.org/W4375869423","https://openalex.org/W4379984888","https://openalex.org/W6638523607","https://openalex.org/W6677103964","https://openalex.org/W6678583879","https://openalex.org/W6749825310","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2040545019","https://openalex.org/W2787352659","https://openalex.org/W2487162673","https://openalex.org/W2990636717"],"abstract_inverted_index":{"In":[0,113],"recent":[1],"years,":[2],"a":[3,61,80,84,143],"great":[4],"deal":[5],"of":[6,108,187,223,231],"research":[7,103],"has":[8],"focused":[9,92],"on":[10,93,104,199],"in":[11,39,74,134,165,191],"developing":[12],"neural":[13],"network":[14,181],"(NN)-based":[15],"speech":[16],"enhancement":[17,221],"(SE)":[18],"models,":[19],"which":[20,75,125,183],"have":[21],"achieved":[22],"promising":[23],"results.":[24],"However,":[25],"NN-based":[26],"models":[27,110],"typically":[28],"require":[29],"expensive":[30],"computations":[31],"to":[32,83,130,140,151,155,175],"achieve":[33],"remarkable":[34],"performance,":[35],"constraining":[36],"their":[37],"deployment":[38],"real-world":[40],"scenarios,":[41],"especially":[42],"when":[43,49],"hardware":[44],"resources":[45],"are":[46,52,197],"limited":[47],"or":[48],"latency":[50],"requirements":[51],"strict.":[53],"To":[54],"reduce":[55],"this":[56,114],"computational":[57],"burden,":[58],"we":[59,116],"propose":[60],"unified":[62],"residual":[63,121],"fusion":[64,123],"probabilistic":[65,146,163],"knowledge":[66,76,132],"distillation":[67,147,171,215],"(KD)":[68],"method":[69],"for":[70],"the":[71,95,105,119,127,166,176,185,188,192,209,220,224,232],"SE":[72,189,203],"task,":[73],"is":[77,111,149,173],"transferred":[78],"from":[79,138],"deep":[81],"teacher":[82,136],"shallower":[85],"student":[86,128,226],"model.":[87],"Previous":[88],"KD":[89,211],"approaches":[90],"commonly":[91],"narrowing":[94],"output":[96],"distances":[97],"between":[98],"teachers":[99],"and":[100,160,201,217],"students,":[101],"but":[102],"intermediate":[106],"representation":[107,167],"these":[109],"lacking.":[112],"paper,":[115],"first":[117],"study":[118],"cross-layer":[120],"feature":[122],"strategy,":[124],"enables":[126],"model":[129,227],"distill":[131],"contained":[133],"multiple":[135],"layers":[137],"shallow":[139],"deep.":[141],"Second,":[142],"frame":[144],"weighting":[145],"loss":[148],"proposed":[150,170,210],"assign":[152],"more":[153],"emphasis":[154],"frames":[156],"containing":[157],"essential":[158],"information":[159],"preserve":[161],"pairwise":[162],"similarities":[164],"space.":[168],"The":[169],"framework":[172],"applied":[174],"dual-path":[177],"dilated":[178],"convolutional":[179],"recurrent":[180],"(DPDCRN),":[182],"won":[184],"championship":[186],"track":[190],"L3DAS23":[193],"challenge.":[194],"Extensive":[195],"experiments":[196],"conducted":[198],"single-channel":[200],"multichannel":[202],"datasets.":[204],"Objective":[205],"evaluations":[206],"show":[207],"that":[208],"strategy":[212],"outperforms":[213],"other":[214],"methods":[216],"considerably":[218],"improves":[219],"effect":[222],"low-complexity":[225],"(with":[228],"only":[229],"17%":[230],"teacher's":[233],"parameters).":[234]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}