{"id":"https://openalex.org/W4400057702","doi":"https://doi.org/10.1186/s13636-024-00356-4","title":"GLFER-Net: a polyphonic sound source localization and detection network based on global-local feature extraction and recalibration","display_name":"GLFER-Net: a polyphonic sound source localization and detection network based on global-local feature extraction and recalibration","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400057702","doi":"https://doi.org/10.1186/s13636-024-00356-4"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-024-00356-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00356-4","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s13636-024-00356-4","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100578485","display_name":"Mengzhen Ma","orcid":"https://orcid.org/0009-0004-3086-2805"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhen Ma","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing, Urumqi, Xinjiang, China","School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Urumqi, Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing, Urumqi, Xinjiang, China","School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China"],"raw_orcid":"https://orcid.org/0000-0001-7505-1767","affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing, Urumqi, Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100757355","display_name":"Hao Huang","orcid":"https://orcid.org/0009-0005-7353-3072"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang Univerity, Urumqi, Xinjiang, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":{"value":1890,"currency":"USD","value_usd":1890},"apc_paid":{"value":1890,"currency":"USD","value_usd":1890},"fwci":1.6294,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83444766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2024","issue":"1","first_page":null,"last_page":null},"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":0.9998000264167786,"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":0.993399977684021,"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/polyphony","display_name":"Polyphony","score":0.8405880928039551},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6251652836799622},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6059113144874573},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5987533330917358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.590701699256897},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.5552668571472168},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.54311603307724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47188058495521545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4152368903160095},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36232250928878784},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2939419746398926},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12719875574111938},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07510143518447876},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06695127487182617}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8405880928039551},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6251652836799622},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6059113144874573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5987533330917358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.590701699256897},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.5552668571472168},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.54311603307724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47188058495521545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4152368903160095},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36232250928878784},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2939419746398926},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12719875574111938},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07510143518447876},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06695127487182617},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-024-00356-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00356-4","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b5fbdcd2e5e04128a8e197a9fe9d9aa0","is_oa":false,"landing_page_url":"https://doaj.org/article/b5fbdcd2e5e04128a8e197a9fe9d9aa0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2024, Iss 1, Pp 1-16 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-024-00356-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-024-00356-4","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2039240409","https://openalex.org/W2752782242","https://openalex.org/W2810934215","https://openalex.org/W2884585870","https://openalex.org/W2963125010","https://openalex.org/W2981609437","https://openalex.org/W2982382207","https://openalex.org/W2982680886","https://openalex.org/W2998139081","https://openalex.org/W3000352647","https://openalex.org/W3009685637","https://openalex.org/W3034421924","https://openalex.org/W3034552520","https://openalex.org/W3084798277","https://openalex.org/W3094897602","https://openalex.org/W3097777922","https://openalex.org/W3119205652","https://openalex.org/W3162512931","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3191088441","https://openalex.org/W3197097128","https://openalex.org/W3203177955","https://openalex.org/W3206329344","https://openalex.org/W4220894144","https://openalex.org/W4283311932","https://openalex.org/W4283642889","https://openalex.org/W4321770347","https://openalex.org/W4324116353","https://openalex.org/W4372267873","https://openalex.org/W4375868779","https://openalex.org/W4380032323","https://openalex.org/W4382787045","https://openalex.org/W6600281463"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"Abstract":[0],"Polyphonic":[1],"sound":[2,15,38,75,97],"source":[3],"localization":[4,95],"and":[5,20,23,115,139,182,192,221],"detection":[6],"(SSLD)":[7],"task":[8],"aims":[9],"to":[10,32,69,101,126,165,212],"recognize":[11],"the":[12,33,86,94,119,128,167,174,201],"categories":[13],"of":[14,35,63,74,96,177,218],"events,":[16,76],"identify":[17],"their":[18,25],"onset":[19],"offset":[21],"times,":[22],"detect":[24],"corresponding":[26],"direction-of-arrival":[27],"(DOA),":[28],"where":[29,118],"polyphonic":[30,107],"refers":[31],"occurrence":[34],"multiple":[36,171],"overlapping":[37],"sources":[39],"in":[40,66,84,179],"a":[41,106,160,216],"segment.":[42],"However,":[43],"vanilla":[44],"SSLD":[45,108,194],"methods":[46],"based":[47,110],"on":[48,111],"convolutional":[49],"recurrent":[50],"neural":[51],"network":[52,109],"(CRNN)":[53],"suffer":[54],"from":[55],"insufficient":[56],"feature":[57,113,121,141,147,161],"extraction.":[58],"The":[59,145,197,206],"convolutions":[60],"with":[61,190],"kernel":[62],"single":[64],"scale":[65],"CRNN":[67],"fail":[68],"adequately":[70],"extract":[71,127],"multi-scale":[72,129,140],"features":[73,88,131,169],"which":[77],"have":[78],"diverse":[79],"time-frequency":[80],"characteristics.":[81],"It":[82],"results":[83,198],"that":[85,200],"extracted":[87],"lack":[89],"fine-grained":[90],"information":[91],"helpful":[92],"for":[93,153],"sources.":[98],"In":[99],"response":[100],"these":[102],"challenges,":[103],"we":[104,158,185,208],"propose":[105],"global-local":[112,120],"extraction":[114,142,148],"recalibration":[116,162],"(GLFER-Net),":[117],"(GLF)":[122],"extractor":[123],"is":[124,151],"designed":[125,152,209],"global":[130],"through":[132,215],"an":[133],"omni-directional":[134],"dynamic":[135],"convolution":[136],"(ODConv)":[137],"layer":[138],"(MSFE)":[143],"module.":[144],"local":[146],"(LFE)":[149],"unit":[150],"capturing":[154],"detailed":[155],"information.":[156],"Besides,":[157],"design":[159],"(FR)":[163],"module":[164],"emphasize":[166],"crucial":[168],"along":[170],"dimensions.":[172],"On":[173],"open":[175],"datasets":[176],"Task3":[178],"DCASE":[180],"2021":[181],"2022":[183],"Challenges,":[184],"compared":[186],"our":[187],"proposed":[188],"GLFER-Net":[189,202],"six":[191],"four":[193],"methods,":[195],"respectively.":[196],"show":[199],"achieves":[203],"competitive":[204],"performance.":[205],"modules":[207],"are":[210],"verified":[211],"be":[213],"effective":[214],"series":[217],"ablation":[219],"experiments":[220],"visualization":[222],"analyses.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}