{"id":"https://openalex.org/W4210774825","doi":"https://doi.org/10.1109/asru51503.2021.9688198","title":"3D Spatial Features for Multi-Channel Target Speech Separation","display_name":"3D Spatial Features for Multi-Channel Target Speech Separation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210774825","doi":"https://doi.org/10.1109/asru51503.2021.9688198"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688198","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5038895203","display_name":"Rongzhi Gu","orcid":"https://orcid.org/0000-0003-1861-9170"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongzhi Gu","raw_affiliation_strings":["Peking University,Shenzhen,China","Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University,Shenzhen,China","institution_ids":["https://openalex.org/I4210128628"]},{"raw_affiliation_string":"Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102835232","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-2874-5795"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab,Bellevue,USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Bellevue,USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038895203"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":1.0325,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83310902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1002"},"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":0.9984999895095825,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7931996583938599},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.642235517501831},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6287126541137695},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6202505826950073},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6033623218536377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5917130708694458},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48287156224250793},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.44791141152381897},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4299989342689514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41890838742256165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4035794734954834},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11973974108695984},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.07613280415534973},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07491269707679749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931996583938599},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.642235517501831},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6287126541137695},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6202505826950073},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6033623218536377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5917130708694458},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48287156224250793},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.44791141152381897},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4299989342689514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41890838742256165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4035794734954834},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11973974108695984},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.07613280415534973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07491269707679749},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688198","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2099940712","https://openalex.org/W2117678320","https://openalex.org/W2766901645","https://openalex.org/W2885976210","https://openalex.org/W2897977894","https://openalex.org/W2900893004","https://openalex.org/W2909607850","https://openalex.org/W2939360348","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2972693890","https://openalex.org/W2972802573","https://openalex.org/W2973062255","https://openalex.org/W3008400075","https://openalex.org/W3011424113","https://openalex.org/W3099330747","https://openalex.org/W4289665794"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W4223965079","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059","https://openalex.org/W2041060376","https://openalex.org/W3119734852"],"abstract_inverted_index":{"The":[0,137],"use":[1],"of":[2,23,39,54,71,124],"speaker's":[3,27],"directional":[4,28,101],"information":[5,29,70],"for":[6,60],"speech":[7,10,62],"sepa-ration":[8],"and":[9,78,140,149,154,166],"recognition":[11,180],"has":[12],"demonstrated":[13],"the":[14,31,36,67,72,79,82,98,121,172,179],"state-of-the-art":[15],"performances":[16],"on":[17,144],"multi-talker":[18],"scenarios.":[19],"One":[20],"major":[21],"limitation":[22],"previous":[24],"approaches":[25],"using":[26],"is":[30,116,134],"significant":[32],"performance":[33,174],"degradation":[34],"when":[35],"coming":[37],"directions":[38],"two":[40,94],"sound":[41],"sources":[42],"are":[43,91,103],"close.":[44],"To":[45],"address":[46],"these":[47,125],"challenges,":[48],"this":[49,89],"paper":[50],"proposed":[51,138,162],"a":[52,129],"set":[53],"new":[55],"three-dimensional":[56],"(3D)":[57],"spatial":[58,107,112,127,164],"features":[59,102,139,165],"target":[61,73],"sep-aration,":[63],"by":[64],"leveraging":[65],"all":[66],"3D":[68,106,126,163],"location":[69],"speaker,":[74],"including":[75],"azimuth,":[76],"elevation,":[77],"distance":[80],"to":[81,105,119],"microphone":[83,130],"array":[84],"center.":[85],"Previous":[86],"works":[87],"in":[88,93],"area":[90],"extended":[92],"important":[95],"directions.":[96],"First,":[97],"traditional":[99],"1D":[100],"generalized":[104],"features.":[108],"Thus":[109],"more":[110],"discriminative":[111],"diversity":[113],"between":[114],"speakers":[115],"achieved.":[117],"Second,":[118],"unleash":[120],"full":[122],"power":[123],"features,":[128],"pair-wise":[131],"attention":[132,167],"model":[133],"also":[135],"proposed.":[136],"models":[141,168],"were":[142],"evaluated":[143],"both":[145,161],"simulated":[146],"reverberant":[147],"datasets":[148],"real":[150],"recordings":[151],"under":[152],"near":[153],"far-field":[155],"conditions.":[156],"Exper-imental":[157],"results":[158],"show":[159],"that":[160],"can":[169],"significantly":[170],"improve":[171],"separation":[173],"as":[175,177],"well":[176],"reducing":[178],"error":[181],"rate.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}