{"id":"https://openalex.org/W4410288932","doi":"https://doi.org/10.1587/transfun.2025eap1011","title":"Monaural Speech Enhancement with Attention Augmented Dual-Path CRN and Short Time Discrete Cosine Transform","display_name":"Monaural Speech Enhancement with Attention Augmented Dual-Path CRN and Short Time Discrete Cosine Transform","publication_year":2025,"publication_date":"2025-05-12","ids":{"openalex":"https://openalex.org/W4410288932","doi":"https://doi.org/10.1587/transfun.2025eap1011"},"language":"en","primary_location":{"id":"doi:10.1587/transfun.2025eap1011","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2025eap1011","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2025EAP1011/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2025EAP1011/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102779662","display_name":"Lin Zhou","orcid":"https://orcid.org/0000-0003-2898-5633"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Lin ZHOU","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tongjia YAN","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Tongjia YAN","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443403","display_name":"Mingyang Li","orcid":"https://orcid.org/0000-0001-5973-7574"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mingyang LI","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359738","display_name":"Ao Li","orcid":"https://orcid.org/0000-0002-6364-1898"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Ao LI","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090971"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09801697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E108.A","issue":"11","first_page":"1444","last_page":"1451"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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":0.9444000124931335,"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":0.9355999827384949,"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/monaural","display_name":"Monaural","score":0.851587176322937},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.6671963930130005},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6024636626243591},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5784807205200195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5515777468681335},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.501641035079956},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4993245601654053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22450393438339233},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10309916734695435},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0789884626865387}],"concepts":[{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.851587176322937},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6671963930130005},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6024636626243591},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5784807205200195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5515777468681335},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.501641035079956},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4993245601654053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22450393438339233},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10309916734695435},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0789884626865387},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transfun.2025eap1011","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2025eap1011","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2025EAP1011/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transfun.2025eap1011","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2025eap1011","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2025EAP1011/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6249807887","display_name":null,"funder_award_id":"2020YFC2004003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7281439395","display_name":null,"funder_award_id":"2020YFC2004002","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410288932.pdf","grobid_xml":"https://content.openalex.org/works/W4410288932.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2476548250","https://openalex.org/W2517760955","https://openalex.org/W2603567530","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2889442120","https://openalex.org/W2892110446","https://openalex.org/W2963453742","https://openalex.org/W2998161426","https://openalex.org/W3003792425","https://openalex.org/W3015199127","https://openalex.org/W3015485199","https://openalex.org/W3024869864","https://openalex.org/W3081955528","https://openalex.org/W3096408984","https://openalex.org/W3151851237","https://openalex.org/W3191448984","https://openalex.org/W3197627016","https://openalex.org/W3198680319","https://openalex.org/W4224917453","https://openalex.org/W4308455602","https://openalex.org/W4385822611","https://openalex.org/W4405429509"],"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/W2944394647","https://openalex.org/W2072124114","https://openalex.org/W2538939196"],"abstract_inverted_index":{"In":[0],"recent":[1,153],"years,":[2],"the":[3,31,37,46,64,85,97,117,130,170,174],"performance":[4,149,171],"of":[5,36,48,132,173],"phase-aware":[6],"speech":[7,154],"enhancement":[8,155],"neural":[9],"networks":[10],"has":[11],"steadily":[12],"improved.":[13],"However,":[14],"dealing":[15],"with":[16,67],"complex-valued":[17],"Short-Time":[18,53],"Fourier":[19],"Transform":[20,56],"(STFT)":[21],"spectrograms":[22,58],"involves":[23],"complex":[24],"operations":[25],"and":[26,33,50,70,99,108,124,138],"phase":[27,68],"estimation,":[28],"which":[29,62],"increases":[30],"complexity":[32],"parameter":[34,166],"number":[35],"model.":[38],"To":[39,74],"address":[40],"this,":[41],"we":[42,82,90,127],"have":[43,83,91,112,128],"built":[44],"upon":[45],"foundation":[47],"DCTCRN":[49,175],"introduced":[51,114],"real-valued":[52],"Discrete":[54],"Cosine":[55],"(STDCT)":[57],"as":[59,116],"input":[60],"features,":[61],"avoids":[63],"complexities":[65],"associated":[66],"estimation":[69],"modeling":[71],"amplitude-phase":[72],"relationships.":[73],"further":[75],"enhance":[76],"skip":[77],"connections":[78],"without":[79],"increasing":[80],"parameters,":[81],"incorporated":[84],"SimAM":[86],"attention":[87,136],"mechanism.":[88],"Additionally,":[89],"added":[92],"dual-path":[93],"RNN":[94],"modules":[95],"between":[96],"encoder":[98],"decoder":[100],"to":[101,152],"capture":[102],"long":[103],"dependencies":[104],"in":[105,147],"both":[106],"time":[107],"frequency":[109],"dimensions.":[110],"We":[111],"also":[113],"Hardtanh":[115,139],"new":[118],"scaling":[119,140],"function.":[120,141],"Through":[121],"comparative":[122],"experiments":[123],"ablation":[125],"studies,":[126],"confirmed":[129],"effectiveness":[131],"using":[133],"STDCT":[134],"spectrograms,":[135],"mechanism":[137],"Our":[142],"approach":[143],"demonstrates":[144],"higher":[145],"competitiveness":[146],"objective":[148],"metrics":[150],"compared":[151],"models.":[156,177],"Notably,":[157],"it":[158],"achieves":[159],"this":[160],"while":[161],"maintaining":[162],"a":[163],"relatively":[164],"low":[165],"number,":[167],"thus":[168],"raising":[169],"ceiling":[172],"series":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}