{"id":"https://openalex.org/W4297841422","doi":"https://doi.org/10.21437/interspeech.2022-10493","title":"MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources","display_name":"MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841422","doi":"https://doi.org/10.21437/interspeech.2022-10493"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10493","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10493","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5102013209","display_name":"Haoran Yin","orcid":"https://orcid.org/0000-0002-6141-7681"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Yin","raw_affiliation_strings":["ICT Products & Solutions, Huawei, Dongguan, China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"ICT Products & Solutions, Huawei, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675868","display_name":"Ge Meng","orcid":"https://orcid.org/0000-0002-7205-5532"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032187620","display_name":"Yanjie Fu","orcid":"https://orcid.org/0000-0002-1767-8024"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjie Fu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013437068","display_name":"Gaoyan Zhang","orcid":"https://orcid.org/0000-0002-6791-9658"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoyan Zhang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433899","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2078-4215"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["ICT Products & Solutions, Huawei, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"ICT Products & Solutions, Huawei, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750859","display_name":"Lin Qiu","orcid":"https://orcid.org/0000-0003-1236-2191"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Qiu","raw_affiliation_strings":["ICT Products & Solutions, Huawei, Dongguan, China"],"affiliations":[{"raw_affiliation_string":"ICT Products & Solutions, Huawei, Dongguan, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102013209"],"corresponding_institution_ids":["https://openalex.org/I162868743","https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.3677,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51121643,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"891","last_page":"895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9970999956130981,"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/mimo","display_name":"MIMO","score":0.7697382569313049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6911584734916687},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5362699627876282},{"id":"https://openalex.org/keywords/3g-mimo","display_name":"3G MIMO","score":0.4584594964981079},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4550032615661621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3760228157043457},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.33315056562423706},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.30452197790145874},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.28657329082489014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16675472259521484},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06833678483963013}],"concepts":[{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.7697382569313049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6911584734916687},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5362699627876282},{"id":"https://openalex.org/C165650700","wikidata":"https://www.wikidata.org/wiki/Q4636347","display_name":"3G MIMO","level":4,"score":0.4584594964981079},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4550032615661621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3760228157043457},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.33315056562423706},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.30452197790145874},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.28657329082489014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16675472259521484},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06833678483963013}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10493","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10493","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":33,"referenced_works":["https://openalex.org/W280592816","https://openalex.org/W1522301498","https://openalex.org/W2006424233","https://openalex.org/W2096429319","https://openalex.org/W2114219351","https://openalex.org/W2127851351","https://openalex.org/W2155524176","https://openalex.org/W2157331557","https://openalex.org/W2291877678","https://openalex.org/W2586642235","https://openalex.org/W2763188033","https://openalex.org/W2772736377","https://openalex.org/W2888842465","https://openalex.org/W2964342924","https://openalex.org/W2982429715","https://openalex.org/W2987372735","https://openalex.org/W3011424113","https://openalex.org/W3011890046","https://openalex.org/W3015806514","https://openalex.org/W3081461453","https://openalex.org/W3101330598","https://openalex.org/W3132182240","https://openalex.org/W3132830522","https://openalex.org/W3138975519","https://openalex.org/W3157787880","https://openalex.org/W3160649118","https://openalex.org/W3160878746","https://openalex.org/W3162341667","https://openalex.org/W3197954120","https://openalex.org/W4224918929","https://openalex.org/W4287208417","https://openalex.org/W4287394172","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2038397443","https://openalex.org/W4200145345","https://openalex.org/W2112785353","https://openalex.org/W2941374357","https://openalex.org/W1561113522","https://openalex.org/W1495906304","https://openalex.org/W1993205288","https://openalex.org/W4390496060","https://openalex.org/W1520753245","https://openalex.org/W2529849760"],"abstract_inverted_index":{"Recent":[0],"neural":[1],"network":[2,84],"based":[3],"Direction":[4],"of":[5,16,38,96,103,114,118,125],"Arrival":[6],"(DoA)":[7],"estimation":[8],"algorithms":[9,20,47],"have":[10],"performed":[11],"well":[12],"on":[13,50],"unknown":[14],"number":[15,117],"sound":[17,63,98,119,131,141],"sources":[18,64,120,142,174],"scenarios.These":[19],"are":[21,65],"usually":[22],"achieved":[23],"by":[24],"mapping":[25],"the":[26,31,55,59,62,87,93,101,104,111,116,137,167,181,187],"multi-channel":[27,78],"audio":[28],"input":[29,79],"to":[30],"single":[32],"output":[33],"(i.e.overall":[34],"spatial":[35,106],"pseudo-spectrum":[36],"(SPS)":[37],"all":[39],"sources),":[40],"that":[41,58,149],"is":[42,129],"called":[43,85],"MISO.However,":[44],"such":[45],"MISO":[46,89,168],"strongly":[48],"depend":[49],"empirical":[51],"threshold":[52,112,182],"setting":[53,183],"and":[54,80,136,154,159,185],"angle":[56,188],"assumption":[57,189],"angles":[60],"between":[61,140],"greater":[66],"than":[67],"a":[68,76,130],"fixed":[69],"angle.To":[70],"address":[71],"these":[72],"limitations,":[73],"we":[74],"propose":[75],"novel":[77],"multiple":[81],"outputs":[82],"DoA":[83],"MIMO-DoAnet.Unlike":[86],"general":[88],"algorithms,":[90],"MIMO-DoAnet":[91,150,179],"predicts":[92],"SPS":[94],"coding":[95],"each":[97,134],"source":[99,132],"with":[100,166],"help":[102],"informative":[105],"covariance":[107],"matrix.By":[108],"doing":[109],"so,":[110],"task":[113,124],"detecting":[115,126],"becomes":[121],"an":[122],"easier":[123],"whether":[127],"there":[128],"in":[133,171],"output,":[135],"serious":[138],"interaction":[139],"disappears":[143],"during":[144],"inference":[145],"stage.Experimental":[146],"results":[147,176],"show":[148],"achieves":[151],"relative":[152,157],"18.6%":[153],"absolute":[155,160],"13.3%,":[156],"34.4%":[158],"20.2%":[161],"F1":[162],"score":[163],"improvement":[164],"compared":[165],"baseline":[169],"system":[170],"3,":[172],"4":[173],"scenes.The":[175],"also":[177],"demonstrate":[178],"alleviates":[180],"problem":[184,190],"solves":[186],"effectively.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-10-01T00:00:00"}
