{"id":"https://openalex.org/W3096408984","doi":"https://doi.org/10.21437/interspeech.2020-2537","title":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","display_name":"DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096408984","doi":"https://doi.org/10.21437/interspeech.2020-2537","mag":"3096408984"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2537","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101330960","display_name":"Yanxin Hu","orcid":"https://orcid.org/0009-0009-4388-8883"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxin Hu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321915","display_name":"Yun Liu","orcid":"https://orcid.org/0000-0001-5753-1265"},"institutions":[{"id":"https://openalex.org/I4210134178","display_name":"Sohu (China)","ror":"https://ror.org/02sfdh709","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liu","raw_affiliation_strings":["AI Interaction Division, Sogou Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., Beijing, China","institution_ids":["https://openalex.org/I4210134178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017208328","display_name":"Shubo Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubo Lv","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049054911","display_name":"Mengtao Xing","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengtao Xing","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630316","display_name":"Shimin Zhang","orcid":"https://orcid.org/0009-0004-4344-5218"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shimin Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010250251","display_name":"Yihui Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihui Fu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089393598","display_name":"Bihong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134178","display_name":"Sohu (China)","ror":"https://ror.org/02sfdh709","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bihong Zhang","raw_affiliation_strings":["AI Interaction Division, Sogou Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Interaction Division, Sogou Inc., Beijing, China","institution_ids":["https://openalex.org/I4210134178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":701,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2472","last_page":"2476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9796000123023987,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"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":0.9779999852180481,"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/computer-science","display_name":"Computer science","score":0.754240870475769},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7334485054016113},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.5483987927436829},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47862309217453003},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44996967911720276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34145447611808777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09212037920951843},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0898067057132721},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06624066829681396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754240870475769},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7334485054016113},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.5483987927436829},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47862309217453003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44996967911720276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34145447611808777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09212037920951843},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0898067057132721},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06624066829681396},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2537","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1482149378","https://openalex.org/W1516630152","https://openalex.org/W1677182931","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W2031647436","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2086139506","https://openalex.org/W2117678320","https://openalex.org/W2141411743","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2404892923","https://openalex.org/W2792764867","https://openalex.org/W2889442120","https://openalex.org/W2935693977","https://openalex.org/W2940275453","https://openalex.org/W2944972166","https://openalex.org/W2949756029","https://openalex.org/W2952218014","https://openalex.org/W2963045393","https://openalex.org/W2963452667","https://openalex.org/W2963751183","https://openalex.org/W2994988791","https://openalex.org/W2998161426","https://openalex.org/W3015199127","https://openalex.org/W3016120385","https://openalex.org/W3097906045","https://openalex.org/W4394641246"],"related_works":["https://openalex.org/W1600259599","https://openalex.org/W1630865680","https://openalex.org/W2373767407","https://openalex.org/W4214692512","https://openalex.org/W3176700874","https://openalex.org/W2056031932","https://openalex.org/W3168109306","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"has":[2,83],"benefited":[3],"from":[4],"the":[5,56,95,110,154,165,170],"success":[6],"of":[7,12,175],"deep":[8],"learning":[9],"in":[10,51,100,173],"terms":[11,174],"intelligibility":[13],"and":[14,58,63,77,123,167],"perceptual":[15],"quality.Conventional":[16],"time-frequency":[17],"(TF)":[18],"domain":[19],"methods":[20],"focus":[21],"on":[22,141],"predicting":[23,55],"TF-masks":[24],"or":[25,35,61,143],"speech":[26],"spectrum,":[27],"via":[28],"a":[29,46,52,72,105],"naive":[30],"convolution":[31,67],"neural":[32,37],"network":[33,38,69,107],"(CNN)":[34],"recurrent":[36,68],"(RNN).Some":[39],"recent":[40],"studies":[41],"use":[42],"complex-valued":[43,111,128],"spectrogram":[44],"as":[45],"training":[47],"target":[48,97],"but":[49],"train":[50,94],"real-valued":[53],"network,":[54],"magnitude":[57],"phase":[59],"component":[60],"real":[62],"imaginary":[64],"part,":[65],"respectively.Particularly,":[66],"(CRN)":[70],"integrates":[71],"convolutional":[73],"encoder-decoder":[74],"(CED)":[75],"structure":[76,108],"long":[78],"short-term":[79],"memory":[80],"(LSTM),":[81],"which":[82],"been":[84],"proven":[85],"to":[86,93,153],"be":[87],"helpful":[88],"for":[89,164,169],"complex":[90,96],"targets.In":[91],"order":[92],"more":[98],"effectively,":[99],"this":[101],"paper,":[102],"we":[103],"design":[104],"new":[106],"simulating":[109],"operation,":[112],"called":[113],"Deep":[114,157],"Complex":[115],"Convolution":[116],"Recurrent":[117],"Network":[118],"(DCCRN),":[119],"where":[120],"both":[121],"CNN":[122],"RNN":[124],"structures":[125],"can":[126],"handle":[127],"operation.The":[129],"proposed":[130],"DCCRN":[131,150],"models":[132,151],"are":[133],"very":[134],"competitive":[135],"over":[136],"other":[137],"previous":[138],"networks,":[139],"either":[140],"objective":[142],"subjective":[144],"metric.With":[145],"only":[146],"3.7M":[147],"parameters,":[148],"our":[149],"submitted":[152],"Interspeech":[155],"2020":[156],"Noise":[158],"Suppression":[159],"(DNS)":[160],"challenge":[161],"ranked":[162],"first":[163],"real-time-track":[166],"second":[168],"non-real-time":[171],"track":[172],"Mean":[176],"Opinion":[177],"Score":[178],"(MOS).":[179]},"counts_by_year":[{"year":2026,"cited_by_count":47},{"year":2025,"cited_by_count":134},{"year":2024,"cited_by_count":152},{"year":2023,"cited_by_count":161},{"year":2022,"cited_by_count":132},{"year":2021,"cited_by_count":71},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
