{"id":"https://openalex.org/W4372347014","doi":"https://doi.org/10.1109/icassp49357.2023.10094862","title":"Exploiting Speaker Embeddings for Improved Microphone Clustering and Speech Separation in ad-hoc Microphone Arrays","display_name":"Exploiting Speaker Embeddings for Improved Microphone Clustering and Speech Separation in ad-hoc Microphone Arrays","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372347014","doi":"https://doi.org/10.1109/icassp49357.2023.10094862"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01H142WXB2QWKS0AXR0EHNH2M1/file/01H142ZCSV24C0HAH1FM60R1H1.pdf","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":false,"raw_author_name":"Stijn Kindt","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, 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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","Department of Electronics and Information Systems, IDLab, Ghent University - imec, Ghent, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Ghent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7987029552459717},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7741097807884216},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7599015235900879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6616946458816528},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.652819812297821},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5633648037910461},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.5590168833732605},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5201219320297241},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.516105055809021},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45681652426719666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4550401568412781},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41449493169784546},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31786346435546875},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.09297442436218262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987029552459717},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7741097807884216},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7599015235900879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6616946458816528},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.652819812297821},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5633648037910461},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.5590168833732605},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5201219320297241},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.516105055809021},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45681652426719666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4550401568412781},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41449493169784546},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31786346435546875},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.09297442436218262},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","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":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01H142WXB2QWKS0AXR0EHNH2M1","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01H142WXB2QWKS0AXR0EHNH2M1","pdf_url":"https://biblio.ugent.be/publication/01H142WXB2QWKS0AXR0EHNH2M1/file/01H142ZCSV24C0HAH1FM60R1H1.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01H142WXB2QWKS0AXR0EHNH2M1","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01H142WXB2QWKS0AXR0EHNH2M1","pdf_url":"https://biblio.ugent.be/publication/01H142WXB2QWKS0AXR0EHNH2M1/file/01H142ZCSV24C0HAH1FM60R1H1.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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781728163277","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6899999976158142}],"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/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372347014.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1553180721","https://openalex.org/W1969209815","https://openalex.org/W1995450389","https://openalex.org/W2067295501","https://openalex.org/W2068068201","https://openalex.org/W2071608040","https://openalex.org/W2114155159","https://openalex.org/W2127851351","https://openalex.org/W2129227482","https://openalex.org/W2403891086","https://openalex.org/W2763188033","https://openalex.org/W2808631503","https://openalex.org/W2900388901","https://openalex.org/W3024869864","https://openalex.org/W3179439275","https://openalex.org/W3208740877","https://openalex.org/W4221167533","https://openalex.org/W4312591040","https://openalex.org/W4372269848","https://openalex.org/W6713364637","https://openalex.org/W6738598177","https://openalex.org/W6766360866","https://openalex.org/W6809668307"],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W2914532148","https://openalex.org/W2372625757","https://openalex.org/W4313178214","https://openalex.org/W2383482627","https://openalex.org/W2081900870","https://openalex.org/W3093766508","https://openalex.org/W2012393389","https://openalex.org/W2396048001","https://openalex.org/W1559044324"],"abstract_inverted_index":{"For":[0],"separating":[1],"sources":[2],"captured":[3],"by":[4,86],"ad":[5],"hoc":[6],"distributed":[7],"microphones":[8,16],"a":[9,32,41],"key":[10],"first":[11],"step":[12],"is":[13],"assigning":[14],"the":[15,18,37,48,53,70,87,94,103,111,114,124,132,135,147],"to":[17,131,139],"appropriate":[19,80],"source-dominated":[20],"clusters.":[21],"The":[22],"features":[23,84,99,137],"used":[24],"for":[25,69,93,123],"such":[26],"(blind)":[27],"clustering":[28,115],"are":[29],"based":[30],"on":[31,110],"fixed":[33],"length":[34],"embedding":[35,49,65],"of":[36,72,102,113],"audio":[38],"signals":[39],"in":[40,100,129,146],"high-dimensional":[42],"latent":[43],"space.":[44],"In":[45],"previous":[46],"work,":[47],"was":[50],"hand-engineered":[51,133],"from":[52],"Mel":[54],"frequency":[55],"cepstral":[56],"coefficients":[57],"and":[58,143],"their":[59],"modulation-spectra.":[60],"This":[61],"paper":[62],"argues":[63],"that":[64,128],"frameworks":[66],"designed":[67],"explicitly":[68],"purpose":[71],"reliably":[73],"discriminating":[74],"between":[75],"speakers":[76],"would":[77],"produce":[78],"more":[79,140],"features.":[81],"We":[82,96],"propose":[83],"generated":[85],"state-of-the-art":[88],"ECAPA-TDNN":[89],"speaker":[90],"verification":[91],"model":[92],"clustering.":[95],"benchmark":[97],"these":[98],"terms":[101],"subsequent":[104,148],"signal":[105],"enhancement":[106,149],"as":[107,109],"well":[108],"quality":[112],"where,":[116],"further,":[117],"we":[118],"introduce":[119],"3":[120],"intuitive":[121],"metrics":[122],"latter.":[125],"Results":[126],"indicate":[127],"contrast":[130],"features,":[134],"ECAPA-TDNN-based":[136],"lead":[138],"logical":[141],"clusters":[142],"better":[144],"performance":[145],"stages":[150],"-":[151],"thus":[152],"validating":[153],"our":[154],"hypothesis.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
