{"id":"https://openalex.org/W4414829264","doi":"https://doi.org/10.1109/lsp.2026.3685150","title":"Reverberation-Based Features for Sound Event Localization and Detection With Distance Estimation","display_name":"Reverberation-Based Features for Sound Event Localization and Detection With Distance Estimation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414829264","doi":"https://doi.org/10.1109/lsp.2026.3685150"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2026.3685150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3685150","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.08644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005679652","display_name":"Davide Berghi","orcid":"https://orcid.org/0000-0001-6279-6364"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Davide Berghi","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6279-6364","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-7933-5935","affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech, and Signal Processing, University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005679652"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":30.23,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9789909,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"33","issue":null,"first_page":"1841","last_page":"1845"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9919999837875366,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/event","display_name":"Event (particle physics)","score":0.6802999973297119},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6567999720573425},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.5978000164031982},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48829999566078186},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45730000734329224},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40470001101493835}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6802999973297119},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6452000141143799},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.5978000164031982},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49970000982284546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37229999899864197},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.33500000834465027},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.30720001459121704},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C3017552255","wikidata":"https://www.wikidata.org/wiki/Q4135208","display_name":"Arrival time","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25029999017715454}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/lsp.2026.3685150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2026.3685150","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2504.08644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.08644","pdf_url":"https://arxiv.org/pdf/2504.08644","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2504.08644","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.08644","pdf_url":"https://arxiv.org/pdf/2504.08644","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.08644","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.08644","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.08644","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.08644","pdf_url":"https://arxiv.org/pdf/2504.08644","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sound":[0],"event":[1,10,52,115],"localization":[2,19],"and":[3,87,99,118,122,135],"detection":[4,116],"(SELD)":[5],"involves":[6],"predicting":[7],"active":[8],"sound":[9,51,114],"classes":[11],"over":[12],"time":[13],"while":[14],"estimating":[15],"their":[16],"positions.":[17],"The":[18],"subtask":[20],"in":[21,54],"SELD":[22,38,111,145],"is":[23],"usually":[24],"treated":[25],"as":[26],"a":[27],"direction":[28],"of":[29,50],"arrival":[30],"estimation":[31,120],"problem,":[32],"ignoring":[33],"source":[34],"distance.":[35],"Only":[36],"recently,":[37],"was":[39],"extended":[40],"to":[41,92,132],"3D":[42,55,144],"by":[43,74],"incorporating":[44],"distance":[45,68,140],"estimation,":[46,141],"enabling":[47],"the":[48,83,104],"prediction":[49],"positions":[53],"space":[56],"(3D":[57],"SELD).":[58],"However,":[59],"existing":[60],"methods":[61],"lack":[62],"input":[63],"features":[64,102,112],"specifically":[65],"designed":[66],"for":[67,113],"estimation.":[69],"We":[70,96],"address":[71],"this":[72],"gap":[73],"introducing":[75],"two":[76],"novel":[77],"reverberation-based":[78],"feature":[79],"formats:":[80],"one":[81],"using":[82],"direct-toreverberant":[84],"ratio":[85],"(DRR)":[86],"another":[88],"leveraging":[89],"signal":[90],"autocorrelation":[91],"capture":[93],"early":[94],"reflections.":[95],"extensively":[97],"evaluate":[98],"benchmark":[100],"these":[101],"on":[103],"STARSS23":[105],"dataset,":[106],"combining":[107],"them":[108],"with":[109],"established":[110],"(SED)":[117],"direction-of-arrival":[119],"(DOAE),":[121],"testing":[123],"across":[124],"different":[125],"network":[126],"architectures.":[127],"Our":[128],"proposed":[129],"features,":[130],"applicable":[131],"both":[133],"FOA":[134],"MIC":[136],"formats,":[137],"achieve":[138],"state-of-theart":[139],"enhancing":[142],"overall":[143],"performance.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-13T06:04:23.736269","created_date":"2025-10-05T00:00:00"}