{"id":"https://openalex.org/W4312574411","doi":"https://doi.org/10.1109/icspcc55723.2022.9984356","title":"DPTNet-based Beamforming for Speech Separation","display_name":"DPTNet-based Beamforming for Speech Separation","publication_year":2022,"publication_date":"2022-10-25","ids":{"openalex":"https://openalex.org/W4312574411","doi":"https://doi.org/10.1109/icspcc55723.2022.9984356"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc55723.2022.9984356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc55723.2022.9984356","pdf_url":null,"source":{"id":"https://openalex.org/S4363608295","display_name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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":"2022 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/A5101713797","display_name":"Tongtong Zhao","orcid":"https://orcid.org/0000-0001-8079-8048"},"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":"Tongtong Zhao","raw_affiliation_strings":["Beijing University of Technology,Speech and Audio Signal Processing Laboratory, Faculty of Information Technology,Beijing,China,100124"],"raw_orcid":null,"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"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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/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":false,"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.121,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2968209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/beamforming","display_name":"Beamforming","score":0.7822984457015991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7494416236877441},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.667879581451416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6246817708015442},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5393528938293457},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.44911208748817444},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4413143992424011},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.42527467012405396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42155182361602783},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3252226710319519},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2126818597316742},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14988210797309875},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13943469524383545}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7822984457015991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494416236877441},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.667879581451416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6246817708015442},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5393528938293457},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.44911208748817444},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4413143992424011},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.42527467012405396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42155182361602783},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3252226710319519},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2126818597316742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14988210797309875},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13943469524383545},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc55723.2022.9984356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc55723.2022.9984356","pdf_url":null,"source":{"id":"https://openalex.org/S4363608295","display_name":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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":"2022 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1515932869","https://openalex.org/W1522301498","https://openalex.org/W2055837190","https://openalex.org/W2060108923","https://openalex.org/W2086006777","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2898268964","https://openalex.org/W2964058413","https://openalex.org/W3004309045","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3096893582","https://openalex.org/W3104196160","https://openalex.org/W3163652268","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4387678054","https://openalex.org/W3095575180","https://openalex.org/W2389596151","https://openalex.org/W4221148444","https://openalex.org/W4226054107","https://openalex.org/W4306784355","https://openalex.org/W2510951244","https://openalex.org/W4246226292","https://openalex.org/W2150768546"],"abstract_inverted_index":{"Filter-and-sum":[0],"beamforming":[1,22,59,128],"framework":[2],"could":[3],"separate":[4],"speech":[5,93,107],"effectively":[6],"from":[7],"the":[8,21,25,35,39,48,50,68,86,95,105,112,115,134,146,151,154],"complicated":[9],"acoustic":[10],"scenarios":[11],"by":[12,31],"using":[13],"dual-path":[14,51],"recurrent":[15,32],"neural":[16],"network":[17,53],"(DPRNN)":[18],"to":[19,57,84,109,122,144],"estimate":[20,58],"filters.":[23],"Since":[24],"concerned":[26],"context":[27,89,124],"information":[28,90,125],"was":[29],"modeled":[30],"layers":[33],"of":[34,62,72,91,130,137],"intermediate":[36],"states,":[37],"only":[38],"suboptimal":[40],"separation":[41,160],"performance":[42],"can":[43,157],"be":[44],"achieved.":[45],"To":[46],"increase":[47],"performance,":[49],"transformer":[52],"(DPTNet)":[54],"is":[55,140],"employed":[56],"filters":[60],"instead":[61],"DPRNN":[63],"in":[64],"this":[65],"paper":[66],"because":[67],"DPTNet":[69,116],"takes":[70],"advantage":[71],"self-attention":[73],"mechanism":[74],"and":[75,88,117,142],"makes":[76],"high":[77],"dimension":[78],"feature":[79],"sequences":[80],"interacted":[81],"directly.":[82],"Specifically,":[83],"provide":[85],"spatial":[87],"multi-channel":[92],"signals,":[94],"cosine":[96],"similarities":[97],"between":[98],"different":[99],"channels":[100],"are":[101,120],"first":[102],"concatenated":[103],"with":[104,150],"transformed":[106],"signals":[108],"serve":[110],"as":[111],"input.":[113],"Then,":[114],"transform-averaged-concatenation":[118],"operation":[119],"used":[121],"extract":[123],"for":[126],"estimating":[127],"filter":[129],"each":[131,138],"channel.":[132],"Finally,":[133],"observed":[135],"signal":[136],"channel":[139],"filtered":[141],"added":[143],"obtain":[145],"desired":[147],"speech.":[148],"Compared":[149],"existing":[152],"FaSNet,":[153],"proposed":[155],"method":[156],"achieve":[158],"better":[159],"performance.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}