{"id":"https://openalex.org/W4391307764","doi":"https://doi.org/10.1109/icspcc59353.2023.10400232","title":"A Beam-TFDPRNN Based Speech Separation Method in Reverberant Environments","display_name":"A Beam-TFDPRNN Based Speech Separation Method in Reverberant Environments","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4391307764","doi":"https://doi.org/10.1109/icspcc59353.2023.10400232"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc59353.2023.10400232","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5100437166","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0001-7320-4360"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070475244","display_name":"Changchun Bao","orcid":"https://orcid.org/0000-0002-5606-5343"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Bao","raw_affiliation_strings":["Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104107032","display_name":"Jing Zhou","orcid":"https://orcid.org/0009-0004-6586-0762"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhou","raw_affiliation_strings":["Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064549045","display_name":"Xue Yang","orcid":"https://orcid.org/0000-0001-5846-5319"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Yang","raw_affiliation_strings":["Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100437166"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.6125,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68431925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9988999962806702,"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/reverberation","display_name":"Reverberation","score":0.8109463453292847},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7834763526916504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541112899780273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5561434626579285},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5194377899169922},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45218533277511597},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.44315654039382935},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.42340564727783203},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.4201987385749817},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4001462757587433},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.153958261013031},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11612957715988159},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.0743737518787384},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06847599148750305}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8109463453292847},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7834763526916504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541112899780273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5561434626579285},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5194377899169922},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45218533277511597},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.44315654039382935},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.42340564727783203},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.4201987385749817},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4001462757587433},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.153958261013031},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11612957715988159},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0743737518787384},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06847599148750305},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc59353.2023.10400232","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2640112133","https://openalex.org/W2714487941","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W3015788098","https://openalex.org/W3099330747","https://openalex.org/W3133834828","https://openalex.org/W3151596526","https://openalex.org/W3196940724","https://openalex.org/W3205567090","https://openalex.org/W3211779545","https://openalex.org/W4297841846","https://openalex.org/W4312574411","https://openalex.org/W4312806213","https://openalex.org/W4385807420","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Recently,":[0],"the":[1,6,19,34,42,51,54,59,65,68,73,82,95,104,117,126,139,150,153,171,176,181,194,198,209,214,222],"beamforming":[2,91],"methods":[3],"based":[4,93,207],"on":[5,94,208],"time":[7,35,60,140],"domain":[8,36,61,75,97],"audio":[9,37],"separation":[10,38,196],"network":[11,39],"(Beam-TasNet)":[12],"have":[13,77],"shown":[14],"satisfactory":[15],"performance.":[16],"For":[17],"example,":[18],"performance":[20,48,219],"of":[21,106,152],"minimum":[22],"variance":[23],"distortionless":[24],"response":[25],"(MVDR)":[26],"beamformer":[27,189],"can":[28],"be":[29],"effectively":[30],"improved":[31],"by":[32,64,131,170,174],"using":[33,175],"(TasNet).":[40],"However,":[41],"reverberation":[43,83,157,199],"will":[44],"draw":[45],"a":[46,89,120,162,164,185],"significant":[47],"degradation":[49],"to":[50,124,179,221],"Beam-TasNet":[52],"since":[53],"multiple":[55],"reflection":[56],"sounds":[57],"damage":[58],"features":[62,76,128,147],"extracted":[63],"TasNet.":[66],"Fortunately,":[67],"recent":[69],"studies":[70],"show":[71,212],"that":[72,193,213],"frequency":[74,142],"better":[78,165],"anti-interference":[79],"capability":[80],"in":[81,137,156,197],"environment.":[84],"Therefore,":[85],"this":[86,115],"paper":[87],"proposed":[88,215],"MVDR":[90,188],"method":[92,216],"time-frequency":[96,127,146],"Dual-Path":[98],"Recurrent":[99],"Neural":[100],"Network":[101],"(TFDPRNN)":[102],"for":[103],"task":[105],"speech":[107,135,154,195],"separation,":[108],"and":[109,141],"we":[110],"call":[111],"it":[112],"Beam-TFDPRNN.":[113],"In":[114],"method,":[116],"TFDPRNN":[118],"uses":[119],"path":[121],"scanning":[122,133],"mechanism":[123],"capture":[125],"more":[129,159,186],"comprehensively":[130],"repeatedly":[132],"input":[134],"signal":[136],"both":[138],"dimensions.":[143],"The":[144,204],"scanned":[145],"could":[148],"describe":[149],"characteristics":[151],"sources":[155],"environment":[158,200],"robustly.":[160],"As":[161],"result,":[163],"pre-separation":[166,177],"result":[167],"is":[168,190,201],"obtained":[169,191],"TFDPRNN.":[172],"Furthermore,":[173],"signals":[178],"calculate":[180],"spatial":[182],"covariance":[183],"matrices,":[184],"robust":[187],"so":[192],"achieved":[202],"efficiently.":[203],"experiment":[205],"results":[206],"WSJ0-2mix":[210],"corpus":[211],"achieves":[217],"superior":[218],"compared":[220],"reference":[223],"methods.":[224]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}