{"id":"https://openalex.org/W4388043959","doi":"https://doi.org/10.1186/s13636-023-00310-w","title":"Robustness of ad hoc microphone clustering using speaker embeddings: evaluation under realistic and challenging scenarios","display_name":"Robustness of ad hoc microphone clustering using speaker embeddings: evaluation under realistic and challenging scenarios","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388043959","doi":"https://doi.org/10.1186/s13636-023-00310-w"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00310-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00310-w","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00310-w","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://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00310-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012036252","display_name":"Stijn Kindt","orcid":"https://orcid.org/0000-0001-9300-4251"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Stijn Kindt","raw_affiliation_strings":["IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-9300-4251","affiliations":[{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022199264","display_name":"Jenthe Thienpondt","orcid":"https://orcid.org/0000-0001-5990-722X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jenthe Thienpondt","raw_affiliation_strings":["IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030293327","display_name":"Luca Becker","orcid":null},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luca Becker","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr-Universit\u00e4t Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012036252"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.5219,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63220829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"2023","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":0.9997000098228455,"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":0.9991999864578247,"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/cluster-analysis","display_name":"Cluster analysis","score":0.7948930859565735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7724323272705078},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6519246697425842},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5503649711608887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5387917160987854},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4970605671405792},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.48533669114112854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42264288663864136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39652860164642334},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3371526002883911},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.29369521141052246}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7948930859565735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7724323272705078},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6519246697425842},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5503649711608887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5387917160987854},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4970605671405792},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.48533669114112854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42264288663864136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39652860164642334},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3371526002883911},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29369521141052246},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-023-00310-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00310-w","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00310-w","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:archive.ugent.be:01HFRS1Z1QNGSJPH21GW9PN3QR","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01HFRS1Z1QNGSJPH21GW9PN3QR","pdf_url":"https://biblio.ugent.be/publication/01HFRS1Z1QNGSJPH21GW9PN3QR/file/01HFRS36CKYP3NJ2PHSVWZ2NQX.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"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":"ISSN: 1687-4722","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:4f832e5dd8da4e06bb4c7130c824a01e","is_oa":true,"landing_page_url":"https://doaj.org/article/4f832e5dd8da4e06bb4c7130c824a01e","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2023, Iss 1, Pp 1-20 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00310-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00310-w","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00310-w","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":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1114561054","display_name":null,"funder_award_id":"imec.ICON: BLE2AV","funder_id":"https://openalex.org/F4320313460","funder_display_name":"Agentschap Innoveren en Ondernemen"},{"id":"https://openalex.org/G8050015315","display_name":"Robust speech capture and enhancement using ad hoc distributed microphone arrays by integrating and embedding domain-specific signal models within deep-learning frameworks","funder_award_id":"G081420N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320313460","display_name":"Agentschap Innoveren en Ondernemen","ror":"https://ror.org/032xdry56"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320322603","display_name":"Universiteit Gent","ror":"https://ror.org/00cv9y106"},{"id":"https://openalex.org/F4320323715","display_name":"Ruhr-Universit\u00e4t Bochum","ror":"https://ror.org/04tsk2644"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388043959.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W123936940","https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1553180721","https://openalex.org/W1969209815","https://openalex.org/W1995450389","https://openalex.org/W2067295501","https://openalex.org/W2071608040","https://openalex.org/W2106557043","https://openalex.org/W2114155159","https://openalex.org/W2127851351","https://openalex.org/W2129227482","https://openalex.org/W2219499605","https://openalex.org/W2752782242","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2892163332","https://openalex.org/W2900388901","https://openalex.org/W2902119340","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3038205844","https://openalex.org/W3139695047","https://openalex.org/W3162294994","https://openalex.org/W3166393642","https://openalex.org/W3179439275","https://openalex.org/W4312416532","https://openalex.org/W4372269848","https://openalex.org/W4372347014","https://openalex.org/W4388117446","https://openalex.org/W6912185281"],"related_works":["https://openalex.org/W3119288895","https://openalex.org/W1977167953","https://openalex.org/W2185075503","https://openalex.org/W2749720872","https://openalex.org/W2186375278","https://openalex.org/W2793748347","https://openalex.org/W4229940372","https://openalex.org/W2104528589","https://openalex.org/W2155047054","https://openalex.org/W2002404399"],"abstract_inverted_index":{"Abstract":[0],"Speaker":[1],"embeddings,":[2],"from":[3,80],"the":[4,15,46,49,118,121,126,130,146,149,163,166,173,183,200],"ECAPA-TDNN":[5],"speaker":[6,36,59,184],"verification":[7],"network,":[8],"were":[9],"recently":[10],"introduced":[11],"as":[12,61,117],"features":[13,150],"for":[14,65,171],"task":[16],"of":[17,45,51,76,91,120,148,168,175],"clustering":[18,44,69],"microphones":[19,47],"in":[20,29,106,125,151],"ad":[21,66,177],"hoc":[22,67,178],"arrays.":[23],"Our":[24],"previous":[25],"work":[26,54,88],"demonstrated":[27],"that,":[28],"comparison":[30],"to":[31,56,138,141,188,205],"signal-based":[32],"Mod-MFCC":[33],"features,":[34],"using":[35],"embeddings":[37,60,185],"yielded":[38],"a":[39,62,102],"more":[40,103,107,153],"robust":[41,63,143,187],"and":[42,73,145,156,192,195],"logical":[43,194],"around":[48],"sources":[50,201],"interest.":[52],"This":[53],"aims":[55],"further":[57],"establish":[58],"feature":[64],"microphone":[68],"by":[70],"addressing":[71],"open":[72],"additional":[74,113],"questions":[75],"practical":[77],"interest,":[78],"arising":[79],"our":[81,86],"prior":[82],"work.":[83],"Specifically,":[84],"whereas":[85],"initial":[87],"made":[89],"use":[90],"simulated":[92],"data":[93,136],"based":[94],"on":[95,165],"shoe-box":[96],"acoustics":[97],"models,":[98],"we":[99,111],"now":[100],"present":[101],"thorough":[104],"analysis":[105],"realistic":[108],"settings.":[109],"Furthermore,":[110],"investigate":[112],"important":[114],"considerations":[115],"such":[116,176],"choice":[119],"distance":[122],"metric":[123],"used":[124],"fuzzy":[127],"C-means":[128],"clustering;":[129],"minimal":[131],"time":[132],"range":[133],"across":[134],"which":[135],"need":[137],"be":[139],"aggregated":[140],"obtain":[142],"clusters;":[144],"performance":[147],"increasingly":[152],"challenging":[154],"situations,":[155],"with":[157],"multiple":[158],"speakers.":[159],"We":[160],"also":[161],"contrast":[162],"results":[164],"basis":[167],"several":[169],"metrics":[170],"quantifying":[172],"quality":[174],"clusters.":[179],"Results":[180],"indicate":[181],"that":[182],"are":[186,202],"short":[189],"inference":[190],"times,":[191],"deliver":[193],"useful":[196],"clusters,":[197],"even":[198],"when":[199],"very":[203],"close":[204],"each":[206],"other.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}