{"id":"https://openalex.org/W4407364875","doi":"https://doi.org/10.1186/s13636-025-00393-7","title":"Investigations on higher-order spherical harmonic input features for deep learning-based multiple speaker detection and localization","display_name":"Investigations on higher-order spherical harmonic input features for deep learning-based multiple speaker detection and localization","publication_year":2025,"publication_date":"2025-02-12","ids":{"openalex":"https://openalex.org/W4407364875","doi":"https://doi.org/10.1186/s13636-025-00393-7"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00393-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00393-7","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00393-7.pdf","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"],"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://link.springer.com/content/pdf/10.1186/s13636-025-00393-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048052334","display_name":"Nils Poschadel","orcid":"https://orcid.org/0000-0003-4302-5569"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nils Poschadel","raw_affiliation_strings":["Institute of Communications Technology, Leibniz University Hannover, Appelstr. 9A, 30167, Hannover, Lower Saxony, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4302-5569","affiliations":[{"raw_affiliation_string":"Institute of Communications Technology, Leibniz University Hannover, Appelstr. 9A, 30167, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057183351","display_name":"Stephan Preihs","orcid":"https://orcid.org/0000-0003-4232-580X"},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stephan Preihs","raw_affiliation_strings":["Institute of Communications Technology, Leibniz University Hannover, Appelstr. 9A, 30167, Hannover, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communications Technology, Leibniz University Hannover, Appelstr. 9A, 30167, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056813963","display_name":"J\u00fcrgen Peissig","orcid":null},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I4210136150","display_name":"L3S Research Center","ror":"https://ror.org/039t4wk02","country_code":"DE","type":"facility","lineage":["https://openalex.org/I114112103","https://openalex.org/I4210136150","https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Peissig","raw_affiliation_strings":["Institute of Communications Technology, Leibniz University Hannover, Appelstr. 9A, 30167, Hannover, Lower Saxony, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communications Technology, Leibniz University Hannover, Appelstr. 9A, 30167, Hannover, Lower Saxony, Germany","institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048052334"],"corresponding_institution_ids":["https://openalex.org/I114112103","https://openalex.org/I4210136150"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2753,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74386935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"2025","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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9075742363929749},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5671007633209229},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5290884971618652},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4979875087738037},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.48555538058280945},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.47786229848861694},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4704267978668213},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35259485244750977},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.25621721148490906},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18112215399742126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9075742363929749},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5671007633209229},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5290884971618652},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4979875087738037},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.48555538058280945},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.47786229848861694},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4704267978668213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35259485244750977},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25621721148490906},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18112215399742126},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00393-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00393-7","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00393-7.pdf","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"],"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:9f604393b3184754a3ae527721a4ed45","is_oa":true,"landing_page_url":"https://doaj.org/article/9f604393b3184754a3ae527721a4ed45","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-26 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00393-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00393-7","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00393-7.pdf","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"],"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":[],"awards":[{"id":"https://openalex.org/G4206783497","display_name":null,"funder_award_id":"517437545","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320322379","display_name":"Gottfried Wilhelm Leibniz Universit\u00e4t Hannover","ror":"https://ror.org/0304hq317"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407364875.pdf","grobid_xml":"https://content.openalex.org/works/W4407364875.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1555217905","https://openalex.org/W1970431334","https://openalex.org/W1979601119","https://openalex.org/W1991170630","https://openalex.org/W1995945562","https://openalex.org/W2035083192","https://openalex.org/W2046317813","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2129501075","https://openalex.org/W2222512263","https://openalex.org/W2316138215","https://openalex.org/W2408239454","https://openalex.org/W2494085323","https://openalex.org/W2507219293","https://openalex.org/W2611943505","https://openalex.org/W2734774145","https://openalex.org/W2761615410","https://openalex.org/W2810934215","https://openalex.org/W2883288608","https://openalex.org/W2898395910","https://openalex.org/W2917254586","https://openalex.org/W2940285530","https://openalex.org/W2948091552","https://openalex.org/W2991365756","https://openalex.org/W2994698073","https://openalex.org/W2997721189","https://openalex.org/W2998139081","https://openalex.org/W3015758669","https://openalex.org/W3015806514","https://openalex.org/W3029436999","https://openalex.org/W3083274258","https://openalex.org/W3104757150","https://openalex.org/W3105563130","https://openalex.org/W3113518618","https://openalex.org/W3117312351","https://openalex.org/W3117314925","https://openalex.org/W3127686677","https://openalex.org/W3129370657","https://openalex.org/W3157787880","https://openalex.org/W3163193264","https://openalex.org/W3163881933","https://openalex.org/W3171138738","https://openalex.org/W3184868278","https://openalex.org/W3197097128","https://openalex.org/W3203177955","https://openalex.org/W3206162458","https://openalex.org/W3206329344","https://openalex.org/W3213455868","https://openalex.org/W4205393804","https://openalex.org/W4205574321","https://openalex.org/W4224933823","https://openalex.org/W4229751704","https://openalex.org/W4236344233","https://openalex.org/W4238594354","https://openalex.org/W4243869688","https://openalex.org/W4283759342","https://openalex.org/W4285038153","https://openalex.org/W4312628540","https://openalex.org/W4385822950","https://openalex.org/W4386763588","https://openalex.org/W4388117349","https://openalex.org/W4390096820","https://openalex.org/W4390137121","https://openalex.org/W6960989754"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2376224659","https://openalex.org/W2611989081","https://openalex.org/W2169064893","https://openalex.org/W32484671","https://openalex.org/W4294437891","https://openalex.org/W2731899572","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727"],"abstract_inverted_index":{"Abstract":[0],"In":[1,192],"this":[2],"paper,":[3],"a":[4,44,73],"detailed":[5],"investigation":[6],"of":[7,81,102,179,205],"deep":[8,56],"learning-based":[9,57],"speaker":[10],"detection":[11,82,103],"and":[12,38,83,125,135,174,211,229],"localization":[13],"(SDL)":[14],"with":[15,72,224],"higher-order":[16,30],"Ambisonics":[17,150,213],"signals":[18,158],"is":[19],"conducted.":[20],"Different":[21],"spherical":[22],"harmonic":[23,35],"(SH)":[24],"input":[25,53,190],"features":[26,208],"such":[27],"as":[28,51,94,96,120,122],"the":[29,39,48,78,100,123,172,175,180,194,203,206,217],"pseudointensity":[31,41,182],"vector":[32,42,183],"(HO-PIV),":[33],"relative":[34],"coefficients":[36],"(RHCs),":[37],"spatially-localized":[40],"(SL-PIV),":[43],"feature":[45,54],"proposed":[46,196],"for":[47,55,77,90,151],"first":[49],"time":[50],"an":[52,141],"SDL,":[58],"are":[59,85,109],"examined":[60],"using":[61,156],"first-":[62],"to":[63,148,187,201],"fourth-order":[64,157,212],"SH":[65],"signals.":[66],"The":[67,107,138],"trained":[68],"neural":[69],"networks,":[70],"optimized":[71],"single":[74],"loss":[75],"function":[76],"combined":[79],"tasks":[80],"localization,":[84],"then":[86],"evaluated":[87],"in":[88,99,112,144,216],"detail":[89],"overall":[91,142],"SDL":[92,145],"performance":[93,98,146],"well":[95,121],"their":[97],"sub-tasks":[101],"and,":[104],"particularly,":[105],"localization.":[106],"results":[108],"further":[110,163],"analyzed":[111],"dependence":[113],"on":[114,209,221],"room":[115],"reverberation,":[116],"signal-to-interference":[117],"ratio":[118],"(SIR),":[119],"number":[124],"distances":[126],"between":[127],"multiple":[128],"simultaneously":[129],"active":[130],"speakers,":[131],"utilizing":[132],"both":[133,177],"simulated":[134],"measured":[136,222],"data.":[137],"findings":[139],"indicate":[140],"improvement":[143,164],"up":[147],"third-order":[149],"all":[152],"investigated":[153,207],"features,":[154],"while":[155],"does":[159],"not":[160],"yield":[161],"any":[162],"or":[165],"sometimes":[166],"even":[167],"delivers":[168],"worse":[169],"results.":[170],"Notably,":[171],"HO-PIV":[173],"SL-PIV,":[176],"extensions":[178],"first-order":[181],"(FO-PIV),":[184],"have":[185],"proven":[186],"be":[188,202],"suitable":[189],"features.":[191],"particular":[193],"newly":[195],"SL-PIV":[197],"has":[198],"been":[199],"found":[200],"best":[204],"third-":[210],"signals,":[214],"especially":[215],"most":[218],"demanding":[219],"scenarios":[220],"data,":[223],"multiple,":[225],"closely":[226],"located":[227],"speakers":[228],"poor":[230],"SIR.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-08T06:56:09.383167","created_date":"2025-10-10T00:00:00"}
