{"id":"https://openalex.org/W4200634403","doi":"https://doi.org/10.1109/icassp43922.2022.9747340","title":"DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation and Extraction","display_name":"DPCCN: Densely-Connected Pyramid Complex Convolutional Network for Robust Speech Separation and Extraction","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4200634403","doi":"https://doi.org/10.1109/icassp43922.2022.9747340"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5090367911","display_name":"Jiangyu Han","orcid":"https://orcid.org/0000-0001-5390-8520"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CN","CZ"],"is_corresponding":false,"raw_author_name":"Jiangyu Han","raw_affiliation_strings":["Shanghai Normal University,Shanghai,China","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056415893","display_name":"Yanhua Long","orcid":"https://orcid.org/0000-0003-0924-408X"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhua Long","raw_affiliation_strings":["Shanghai Normal University,Shanghai,China","Unisound AI Technology Co., Ltd., Beijing, China","Shanghai Normal University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Normal University,Shanghai,China","institution_ids":["https://openalex.org/I21945476"]},{"raw_affiliation_string":"Unisound AI Technology Co., Ltd., Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Normal University, Shanghai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology, Speech@FIT, Brno University of Technology, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1787,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90147938,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7292","last_page":"7296"},"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":0.9991999864578247,"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":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8395265936851501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8139317035675049},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5438864231109619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5098509192466736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4931335151195526},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4893631339073181},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4584469497203827},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4320027828216553},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4266628623008728},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42210912704467773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3870770037174225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12541484832763672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08440378308296204}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8395265936851501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8139317035675049},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5438864231109619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5098509192466736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4931335151195526},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4893631339073181},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4584469497203827},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4320027828216553},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4266628623008728},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42210912704467773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3870770037174225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12541484832763672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08440378308296204},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747340","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"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":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W2117678320","https://openalex.org/W2159202424","https://openalex.org/W2221409856","https://openalex.org/W2558649592","https://openalex.org/W2560023338","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2905258586","https://openalex.org/W2952218014","https://openalex.org/W2963242190","https://openalex.org/W2963446712","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015636705","https://openalex.org/W3015843733","https://openalex.org/W3027008958","https://openalex.org/W3042857426","https://openalex.org/W3093839391","https://openalex.org/W3094607766","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3097653961","https://openalex.org/W3099330747","https://openalex.org/W3110852964","https://openalex.org/W3162539493","https://openalex.org/W3163208914","https://openalex.org/W3163652268","https://openalex.org/W3168140565","https://openalex.org/W3197103473","https://openalex.org/W3197629192","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6749825310","https://openalex.org/W6777776875","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W2782295999","https://openalex.org/W1970292246","https://openalex.org/W2162306796","https://openalex.org/W2015118744","https://openalex.org/W4247952185","https://openalex.org/W1642462315","https://openalex.org/W2005619368","https://openalex.org/W2065140124","https://openalex.org/W1879092539","https://openalex.org/W2526155427"],"abstract_inverted_index":{"In":[0,28],"recent":[1],"years,":[2],"a":[3,38,68],"number":[4],"of":[5,15,50,80],"time-domain":[6,146],"speech":[7,51,63,129],"separation":[8,52,130],"methods":[9,108],"have":[10],"been":[11],"proposed.":[12],"However,":[13],"most":[14],"them":[16],"are":[17],"very":[18],"sensitive":[19],"to":[20,46,61,82,92],"the":[21,32,48,59,78,94,101,106,133,143,150,157,164],"environments":[22],"and":[23,113,131,140],"wide":[24],"domain":[25,34,96,178,184],"coverage":[26],"tasks.":[27,86,152],"this":[29],"paper,":[30],"from":[31],"time-frequency":[33],"perspective,":[35],"we":[36,57,75,154],"propose":[37],"densely-connected":[39],"pyramid":[40],"complex":[41],"convolutional":[42],"network,":[43],"termed":[44],"DPCCN,":[45],"improve":[47],"robustness":[49,79,141],"under":[53,111],"complicated":[54],"conditions.":[55,123],"Furthermore,":[56],"generalize":[58],"DPCCN":[60,81,161],"target":[62,95,177],"extraction":[64],"(TSE)":[65],"by":[66],"integrating":[67],"new":[69],"specially":[70],"designed":[71],"speaker":[72],"encoder.":[73],"Moreover,":[74],"also":[76,118],"investigate":[77],"unsupervised":[83,167],"cross-domain":[84,122,151,168],"TSE":[85],"A":[87],"Mixture-Remix":[88,158],"approach":[89],"is":[90],"proposed":[91,107],"adapt":[93],"acoustic":[97],"characteristics":[98],"for":[99,127,149,166],"fine-tuning":[100,159],"source":[102,183],"model.":[103],"We":[104],"evaluate":[105],"not":[109],"only":[110],"noisy":[112],"reverberant":[114],"in-domain":[115],"condition,":[116],"but":[117,121],"in":[119],"clean":[120],"Results":[124],"show":[125],"that":[126,156],"both":[128],"extraction,":[132],"DPCCN-based":[134],"systems":[135],"achieve":[136],"significantly":[137,162],"better":[138],"performance":[139,185],"than":[142],"currently":[144],"dominating":[145],"methods,":[147],"especially":[148],"Particularly,":[153],"find":[155],"with":[160,170],"outperforms":[163],"TD-SpeakerBeam":[165],"TSE,":[169],"around":[171],"3.5":[172],"dB":[173],"SISNR":[174],"improvement":[175],"on":[176],"test":[179],"set,":[180],"without":[181],"any":[182],"degradation.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}