{"id":"https://openalex.org/W4409762166","doi":"https://doi.org/10.1016/j.inffus.2025.103218","title":"Cross-attention among spectrum, waveform and SSL representations with bidirectional knowledge distillation for speech enhancement","display_name":"Cross-attention among spectrum, waveform and SSL representations with bidirectional knowledge distillation for speech enhancement","publication_year":2025,"publication_date":"2025-04-24","ids":{"openalex":"https://openalex.org/W4409762166","doi":"https://doi.org/10.1016/j.inffus.2025.103218"},"language":"en","primary_location":{"id":"doi:10.1016/j.inffus.2025.103218","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2025.103218","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.inffus.2025.103218","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029478820","display_name":"Hang Chen","orcid":"https://orcid.org/0000-0002-0904-8946"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, 230026, Anhui, PR China"],"raw_orcid":"https://orcid.org/0000-0002-0904-8946","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 230026, Anhui, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334368","display_name":"Chenxi Wang","orcid":"https://orcid.org/0000-0002-0174-0911"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, 230026, Anhui, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 230026, Anhui, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434900","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3843-3920"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["University of Science and Technology of China, Hefei, 230026, Anhui, PR China"],"raw_orcid":"https://orcid.org/0000-0003-3843-3920","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 230026, Anhui, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China, Hefei, 230026, Anhui, PR China"],"raw_orcid":"https://orcid.org/0000-0002-2387-0389","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 230026, Anhui, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["University of Palermo, Palermo, 90133, Italy"],"raw_orcid":"https://orcid.org/0000-0002-0770-0507","affiliations":[{"raw_affiliation_string":"University of Palermo, Palermo, 90133, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011133553","display_name":"Genshun Wan","orcid":"https://orcid.org/0000-0002-5813-9430"},"institutions":[{"id":"https://openalex.org/I4210110780","display_name":"HUI Research (Sweden)","ror":"https://ror.org/021t57y21","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210110780"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Genshun Wan","raw_affiliation_strings":["iFLYTEK Research, Hefei, 230088, Anhui, PR China"],"raw_orcid":"https://orcid.org/0000-0002-5813-9430","affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, 230088, Anhui, PR China","institution_ids":["https://openalex.org/I4210110780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924451","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0002-7073-1744"},"institutions":[{"id":"https://openalex.org/I4210110780","display_name":"HUI Research (Sweden)","ror":"https://ror.org/021t57y21","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210110780"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research, Hefei, 230088, Anhui, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research, Hefei, 230088, Anhui, PR China","institution_ids":["https://openalex.org/I4210110780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066886714","display_name":"Huijun Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Ding","raw_affiliation_strings":["Shenzhen University, Shenzhen, 518060, Guangdong, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, 518060, Guangdong, PR China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5066595711"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":{"value":4650,"currency":"USD","value_usd":4650},"apc_paid":{"value":4650,"currency":"USD","value_usd":4650},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08616188,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"122","issue":null,"first_page":"103218","last_page":"103218"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7253992557525635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7184744477272034},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6122358441352844},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.564818263053894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5258073210716248},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4893045127391815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2874893546104431},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.21281743049621582},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08653831481933594}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7253992557525635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7184744477272034},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6122358441352844},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.564818263053894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5258073210716248},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4893045127391815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2874893546104431},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.21281743049621582},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08653831481933594},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.inffus.2025.103218","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2025.103218","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},{"id":"pmh:oai:iris.unipa.it:10447/679550","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/679550","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.inffus.2025.103218","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.inffus.2025.103218","pdf_url":null,"source":{"id":"https://openalex.org/S7560371","display_name":"Information Fusion","issn_l":"1566-2535","issn":["1566-2535","1872-6305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Fusion","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2883237624","display_name":null,"funder_award_id":"62171427","funder_id":"https://openalex.org/F4320325599","funder_display_name":"University of Science and Technology of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2069681747","https://openalex.org/W2070316439","https://openalex.org/W2100495367","https://openalex.org/W2128653836","https://openalex.org/W2134797427","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2146324387","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2294370754","https://openalex.org/W2600383743","https://openalex.org/W2603567530","https://openalex.org/W2734774145","https://openalex.org/W2748787960","https://openalex.org/W2905649134","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2963534679","https://openalex.org/W2964054038","https://openalex.org/W2964058413","https://openalex.org/W2964111476","https://openalex.org/W2972443522","https://openalex.org/W2973049979","https://openalex.org/W2997006708","https://openalex.org/W3015356564","https://openalex.org/W3016120385","https://openalex.org/W3034763882","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3097777922","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3147539069","https://openalex.org/W3160085755","https://openalex.org/W3161140524","https://openalex.org/W3161223924","https://openalex.org/W3162493033","https://openalex.org/W3162501355","https://openalex.org/W3168662520","https://openalex.org/W3174102142","https://openalex.org/W3197284240","https://openalex.org/W3198680319","https://openalex.org/W3201698955","https://openalex.org/W3213188934","https://openalex.org/W4211232265","https://openalex.org/W4221149546","https://openalex.org/W4224917453","https://openalex.org/W4224933800","https://openalex.org/W4226403810","https://openalex.org/W4285119904","https://openalex.org/W4296068772","https://openalex.org/W4296068808","https://openalex.org/W4296069272","https://openalex.org/W4297841575","https://openalex.org/W4307646824","https://openalex.org/W4310852336","https://openalex.org/W4384207766","https://openalex.org/W4385822385","https://openalex.org/W4386608626","https://openalex.org/W4386764361","https://openalex.org/W4392902788","https://openalex.org/W4392903595","https://openalex.org/W4395471007","https://openalex.org/W4404295211","https://openalex.org/W6633117090","https://openalex.org/W6679909955","https://openalex.org/W6681702135","https://openalex.org/W6735443497","https://openalex.org/W6743139828","https://openalex.org/W6748082341","https://openalex.org/W6755751938","https://openalex.org/W6771940864","https://openalex.org/W6787589371","https://openalex.org/W6790758941","https://openalex.org/W6794403492"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"We":[0],"have":[1],"developed":[2],"an":[3],"innovative":[4],"speech":[5],"enhancement":[6],"(SE)":[7],"model":[8,30,39,82,116,155,179],"backbone":[9],"that":[10,152],"utilizes":[11],"cross-attention":[12,51],"among":[13],"spectrum,":[14],"waveform":[15,36,45],"and":[16,35,44,97,141,148,161,184],"self-supervised":[17,61],"learned":[18],"representations":[19],"(CA-SW-SSL)":[20],"to":[21,40,53,129],"integrate":[22],"knowledge":[23,77,105],"from":[24,56],"diverse":[25],"feature":[26],"domains.":[27],"The":[28,84],"CA-SW-SSL":[29,115],"integrates":[31],"the":[32,42,60,67,92,103,111,114,122,131,134,146,153,163,166,173,177],"cross":[33],"spectrum":[34,43],"attention":[37],"(CSWA)":[38],"connect":[41],"branches,":[46],"along":[47],"with":[48,171],"a":[49,75,119],"dual-path":[50],"module":[52],"select":[54],"outputs":[55],"different":[57],"layers":[58],"of":[59,70,133],"learning":[62],"(SSL)":[63],"model.":[64],"To":[65],"handle":[66],"increased":[68],"complexity":[69],"SSL":[71,100],"integration,":[72],"we":[73],"introduce":[74],"bidirectional":[76],"distillation":[78,106],"(BiKD)":[79],"framework":[80],"for":[81],"compression.":[83],"proposed":[85],"adaptive":[86],"layered":[87],"distance":[88],"measure":[89],"(ALDM)":[90],"maximizes":[91],"Gaussian":[93],"likelihood":[94],"between":[95],"clean":[96],"enhanced":[98],"multi-level":[99],"features":[101],"during":[102],"backward":[104],"(BKD)":[107],"process.":[108],"Meanwhile,":[109],"in":[110],"forward":[112],"process,":[113],"acts":[117],"as":[118],"teacher,":[120],"using":[121],"novel":[123],"teacher\u2013student":[124],"Barlow":[125],"Twins":[126],"(TSBT)":[127],"loss":[128],"guide":[130],"training":[132],"CSWA":[135,182],"student":[136],"models,":[137],"including":[138],"both":[139],"lite":[140],"tiny":[142],"versions.":[143],"Experiments":[144],"on":[145,165],"DNS-Challenge":[147,167],"Voicebank+Demand":[149],"datasets":[150],"demonstrate":[151],"CSWA-Lite+BiKD":[154],"outperforms":[156,180],"existing":[157],"joint":[158],"spectrum-waveform":[159],"methods":[160],"surpasses":[162],"state-of-the-art":[164],"non-blind":[168],"test":[169],"set":[170],"half":[172],"computational":[174],"load.":[175],"Further,":[176],"CA-SW-SSL+BiKD":[178],"all":[181],"models":[183],"current":[185],"SSL-based":[186],"methods.":[187]},"counts_by_year":[],"updated_date":"2026-02-07T06:11:34.122080","created_date":"2025-10-10T00:00:00"}
