{"id":"https://openalex.org/W4388820312","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317293","title":"Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction","display_name":"Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388820312","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317293"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317293","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5109656907","display_name":"Aoqi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aoqi Guo","raw_affiliation_strings":["Ocean University of China,China","Ocean University of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Ocean University of China, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846573","display_name":"Junnan Wu","orcid":"https://orcid.org/0009-0001-5621-4011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junnan Wu","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106667221","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0005-7881-712X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045145869","display_name":"Wenbo Zhu","orcid":"https://orcid.org/0000-0001-7835-4990"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbo Zhu","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036138497","display_name":"Qinwen Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinwen Guo","raw_affiliation_strings":["Ocean University of China,China","Ocean University of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Ocean University of China, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033824329","display_name":"Dazhi Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I59028903","display_name":"Ocean University of China","ror":"https://ror.org/04rdtx186","country_code":"CN","type":"education","lineage":["https://openalex.org/I59028903"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dazhi Gao","raw_affiliation_strings":["Ocean University of China,China","Ocean University of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ocean University of China,China","institution_ids":["https://openalex.org/I59028903"]},{"raw_affiliation_string":"Ocean University of China, China","institution_ids":["https://openalex.org/I59028903"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362606","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-8495-9811"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc.,Beijing,China","Xiaomi Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"107","last_page":"113"},"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":0.9983999729156494,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8214776515960693},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6174414157867432},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.554783046245575},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.5358814597129822},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5340619683265686},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.5311986804008484},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5176973342895508},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4931897521018982},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.4256893992424011},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.423565149307251},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4103217124938965},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1614910066127777},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0997033417224884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8214776515960693},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6174414157867432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.554783046245575},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.5358814597129822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5340619683265686},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.5311986804008484},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5176973342895508},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4931897521018982},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4256893992424011},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.423565149307251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4103217124938965},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1614910066127777},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0997033417224884},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317293","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2005602327","https://openalex.org/W2168729028","https://openalex.org/W2291877678","https://openalex.org/W2400339399","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2763188033","https://openalex.org/W2889048668","https://openalex.org/W2909607850","https://openalex.org/W3093839391","https://openalex.org/W3096571892","https://openalex.org/W3162341667","https://openalex.org/W3196360884","https://openalex.org/W3196845798","https://openalex.org/W3196940724","https://openalex.org/W3197097128","https://openalex.org/W3205770165","https://openalex.org/W4210774825","https://openalex.org/W4307199125","https://openalex.org/W4367597591","https://openalex.org/W6754473786","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W818226659","https://openalex.org/W2009075871","https://openalex.org/W2132841313","https://openalex.org/W2105408150","https://openalex.org/W1976800395","https://openalex.org/W2606661315","https://openalex.org/W2548445082","https://openalex.org/W2767070583","https://openalex.org/W636053046","https://openalex.org/W2072054645"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"learning-based":[2],"beamforming":[3],"algorithms":[4],"have":[5],"shown":[6],"promising":[7],"performance":[8,40],"in":[9,76],"target":[10,29,118],"speech":[11,30,64,134],"extraction":[12,31],"tasks.":[13],"However,":[14],"most":[15],"systems":[16],"do":[17],"not":[18],"fully":[19],"utilize":[20],"spatial":[21,35,93,101,124],"information.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,47,80],"propose":[27],"a":[28,82,115,123],"network":[32,121],"that":[33,86,110],"utilizes":[34],"information":[36,69,94,102],"to":[37,53],"enhance":[38],"the":[39,50,59,63,88,100,105,129],"of":[41,62,92,99],"neural":[42,89,130],"beamformer.":[43],"To":[44],"achieve":[45],"this,":[46],"first":[48],"use":[49,98],"UNet-TCN":[51],"structure":[52],"model":[54],"input":[55],"features":[56],"and":[57,122],"improve":[58],"estimation":[60,120],"accuracy":[61],"pre-separation":[65],"module":[66],"by":[67,72,95,104],"avoiding":[68],"loss":[70],"caused":[71],"direct":[73],"dimensionality":[74],"reduction":[75],"other":[77],"models.":[78],"Furthermore,":[79],"introduce":[81],"multi-head":[83],"cross-attention":[84,126],"mechanism":[85,127],"enhances":[87],"beamformer\u2019s":[90],"perception":[91],"making":[96],"full":[97],"received":[103],"array.":[106],"Experimental":[107],"results":[108],"demonstrate":[109],"our":[111],"approach,":[112],"which":[113],"incorporates":[114],"more":[116],"reasonable":[117],"mask":[119],"information-based":[125],"into":[128],"beamformer,":[131],"effectively":[132],"improves":[133],"separation":[135],"performance.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}