{"id":"https://openalex.org/W2943893847","doi":"https://doi.org/10.1109/taslp.2019.2915785","title":"Multiple Sound Source Counting and Localization Based on TF-Wise Spatial Spectrum Clustering","display_name":"Multiple Sound Source Counting and Localization Based on TF-Wise Spatial Spectrum Clustering","publication_year":2019,"publication_date":"2019-05-10","ids":{"openalex":"https://openalex.org/W2943893847","doi":"https://doi.org/10.1109/taslp.2019.2915785","mag":"2943893847"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2915785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2915785","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5086513946","display_name":"Bing Yang","orcid":"https://orcid.org/0000-0002-8978-2322"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bing Yang","raw_affiliation_strings":["Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100410326","display_name":"Hong Liu","orcid":"https://orcid.org/0000-0002-7498-6541"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Liu","raw_affiliation_strings":["Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101483071","display_name":"Cheng Pang","orcid":"https://orcid.org/0000-0001-9631-3658"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Pang","raw_affiliation_strings":["Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Machine Perception, Peking University, Shenzhen Graduate School, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100358313","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot-Saint-Martin, France"],"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rh\u00f4ne-Alpes, Montbonnot-Saint-Martin, France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086513946"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.9854,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91978642,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"8","first_page":"1241","last_page":"1255"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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":0.993399977684021,"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/microphone-array","display_name":"Microphone array","score":0.5633910894393921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.543236255645752},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5224289298057556},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5181535482406616},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4908807873725891},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48528072237968445},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4393782615661621},{"id":"https://openalex.org/keywords/acoustic-source-localization","display_name":"Acoustic source localization","score":0.4357939064502716},{"id":"https://openalex.org/keywords/spatial-correlation","display_name":"Spatial correlation","score":0.4124622046947479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3833504617214203},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3592350482940674},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3308549225330353},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.31287187337875366},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.22772300243377686},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2242654263973236},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.1561121642589569},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12527203559875488}],"concepts":[{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5633910894393921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.543236255645752},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5224289298057556},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5181535482406616},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4908807873725891},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48528072237968445},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4393782615661621},{"id":"https://openalex.org/C93240960","wikidata":"https://www.wikidata.org/wiki/Q217270","display_name":"Acoustic source localization","level":3,"score":0.4357939064502716},{"id":"https://openalex.org/C150060386","wikidata":"https://www.wikidata.org/wiki/Q7574054","display_name":"Spatial correlation","level":2,"score":0.4124622046947479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3833504617214203},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3592350482940674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3308549225330353},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.31287187337875366},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.22772300243377686},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2242654263973236},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.1561121642589569},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12527203559875488},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2019.2915785","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2915785","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2435089432","display_name":null,"funder_award_id":"U1613209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8054616862","display_name":null,"funder_award_id":"61673030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":47,"referenced_works":["https://openalex.org/W633298760","https://openalex.org/W1551673716","https://openalex.org/W1552633171","https://openalex.org/W1605928961","https://openalex.org/W1608401690","https://openalex.org/W1964998538","https://openalex.org/W1966081805","https://openalex.org/W1969299255","https://openalex.org/W1976178451","https://openalex.org/W1987906574","https://openalex.org/W1993678034","https://openalex.org/W2025127228","https://openalex.org/W2030486566","https://openalex.org/W2032647955","https://openalex.org/W2061074721","https://openalex.org/W2068556767","https://openalex.org/W2100818340","https://openalex.org/W2113638573","https://openalex.org/W2116635162","https://openalex.org/W2117029426","https://openalex.org/W2117678320","https://openalex.org/W2124906580","https://openalex.org/W2128026204","https://openalex.org/W2128131274","https://openalex.org/W2151693816","https://openalex.org/W2156642994","https://openalex.org/W2160557558","https://openalex.org/W2163268427","https://openalex.org/W2170393302","https://openalex.org/W2314859257","https://openalex.org/W2339666411","https://openalex.org/W2396045936","https://openalex.org/W2398609788","https://openalex.org/W2403407569","https://openalex.org/W2548487638","https://openalex.org/W2552290276","https://openalex.org/W2615100522","https://openalex.org/W2672714283","https://openalex.org/W2707056040","https://openalex.org/W2749335474","https://openalex.org/W2749964752","https://openalex.org/W3100336094","https://openalex.org/W3127686677","https://openalex.org/W6620445573","https://openalex.org/W6703697878","https://openalex.org/W6712693738","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W4389082013","https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2043735059"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,35,39,48,59,73,76,92,115,119,145,175,178,189],"problem":[4],"of":[5,75,118,177,194],"multiple":[6,182],"sound":[7,90,183],"source":[8,77,134,160,184],"counting":[9,185],"and":[10,45,63,88,162,171,186,196],"localization":[11,187],"in":[12,47,188],"adverse":[13],"acoustic":[14],"environments,":[15],"using":[16,127],"microphone":[17],"array":[18],"recordings.":[19],"The":[20,51,150],"proposed":[21,179],"time-frequency":[22],"(TF)":[23],"wise":[24],"spatial":[25,40,53,82,95,122,129,136,163],"spectrum":[26,54,164],"clustering":[27],"based":[28,57],"method":[29,180],"contains":[30],"two":[31],"stages.":[32],"First,":[33],"given":[34],"received":[36],"sensor":[37],"signals,":[38],"correlation":[41],"matrix":[42],"is":[43,55,125,154],"computed":[44],"denoised":[46],"TF":[49],"domain.":[50],"TF-wise":[52,94],"estimated":[56],"on":[58,167],"signal":[60],"subspace":[61],"information,":[62],"further":[64],"enhanced":[65,93],"by":[66,81,113,156],"an":[67],"exponential":[68],"transform,":[69],"which":[70,124],"can":[71],"increase":[72],"reliability":[74],"presence":[78],"possibility":[79],"reflected":[80],"spectrum.":[83],"Second,":[84],"to":[85,106,140,144],"jointly":[86],"count":[87],"localize":[89],"sources,":[91],"spectra":[96,137],"are":[97,110,138],"divided":[98],"into":[99],"several":[100],"clusters":[101],"with":[102,191],"each":[103,132],"cluster":[104],"corresponding":[105],"one":[107],"source.":[108],"Sources":[109],"successively":[111],"detected":[112,141],"searching":[114],"significant":[116],"peaks":[117],"remaining":[120],"global":[121],"spectrum,":[123],"formed":[126],"unassigned":[128],"spectra.":[130],"After":[131],"new":[133,159],"detection,":[135],"reassigned":[139],"sources":[142,153],"according":[143],"dominance":[146],"association":[147],"between":[148,152],"them.":[149],"interaction":[151],"reduced":[155],"iteratively":[157],"performing":[158],"detection":[161],"assignment.":[165],"Experiments":[166],"both":[168],"simulated":[169],"data":[170,173],"real-world":[172],"demonstrate":[174],"superiority":[176],"for":[181],"environment":[190],"different":[192],"levels":[193],"noise":[195],"reverberation.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}