{"id":"https://openalex.org/W4283072656","doi":"https://doi.org/10.1186/s13636-022-00246-7","title":"DOA-guided source separation with direction-based initialization and time annotations using complex angular central Gaussian mixture models","display_name":"DOA-guided source separation with direction-based initialization and time annotations using complex angular central Gaussian mixture models","publication_year":2022,"publication_date":"2022-06-18","ids":{"openalex":"https://openalex.org/W4283072656","doi":"https://doi.org/10.1186/s13636-022-00246-7"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-022-00246-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00246-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00246-7","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://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00246-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071309390","display_name":"Alexander Bohlender","orcid":"https://orcid.org/0000-0003-1819-0482"},"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":"Alexander Bohlender","raw_affiliation_strings":["IDLab, Department of Electronics and Information Systems, Ghent University - imec, Ghent, Belgium"],"raw_orcid":"https://orcid.org/0000-0003-1819-0482","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/A5071593658","display_name":"Lucas Van Severen","orcid":"https://orcid.org/0000-0002-4766-4360"},"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":"Lucas Van Severen","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/A5087913366","display_name":"Jonathan Sterckx","orcid":"https://orcid.org/0009-0001-1895-9549"},"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":"Jonathan Sterckx","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":"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":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071309390"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04987562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2022","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/T11447","display_name":"Blind Source Separation Techniques","score":0.9984999895095825,"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":0.9950000047683716,"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/initialization","display_name":"Initialization","score":0.8807189464569092},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7414325475692749},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.6061540246009827},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5389912724494934},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5342720150947571},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5236772894859314},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4976671040058136},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4809824228286743},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.46779876947402954},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.46399304270744324},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46350616216659546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4600970149040222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34864169359207153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3312631845474243},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08922672271728516}],"concepts":[{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8807189464569092},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414325475692749},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.6061540246009827},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5389912724494934},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5342720150947571},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5236772894859314},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4976671040058136},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4809824228286743},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.46779876947402954},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.46399304270744324},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46350616216659546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4600970149040222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34864169359207153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3312631845474243},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08922672271728516},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1186/s13636-022-00246-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00246-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00246-7","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:archive.ugent.be:8758927","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8758927","pdf_url":"https://biblio.ugent.be/publication/8758927/file/8758928.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:c317529e625247f79733bb7633541347","is_oa":false,"landing_page_url":"https://doaj.org/article/c317529e625247f79733bb7633541347","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 2022, Iss 1, Pp 1-21 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-022-00246-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00246-7","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-022-00246-7","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":[],"awards":[{"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"},{"id":"https://openalex.org/G816596954","display_name":"Enabling Effortless Communication Under Adverse Conditions by Exploitation of Direction-of-Arrival Estimates and Other A-Priori Knowledge in Joint Acoustic Source Separation and Dereverberation","funder_award_id":"11G0721N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283072656.pdf","grobid_xml":"https://content.openalex.org/works/W4283072656.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W135733562","https://openalex.org/W1549884461","https://openalex.org/W1983812858","https://openalex.org/W2012910847","https://openalex.org/W2018731188","https://openalex.org/W2031583051","https://openalex.org/W2068068201","https://openalex.org/W2099655464","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2149693148","https://openalex.org/W2159956319","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2291372403","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2563666542","https://openalex.org/W2702006285","https://openalex.org/W2884797218","https://openalex.org/W2885219692","https://openalex.org/W2892163332","https://openalex.org/W2892232131","https://openalex.org/W2900212944","https://openalex.org/W2909607850","https://openalex.org/W2933708090","https://openalex.org/W2942172990","https://openalex.org/W2987372735","https://openalex.org/W2993464856","https://openalex.org/W3015661721","https://openalex.org/W3138975519","https://openalex.org/W3160140981","https://openalex.org/W3213559049","https://openalex.org/W4214498238","https://openalex.org/W4231807801"],"related_works":["https://openalex.org/W3049674332","https://openalex.org/W2360629045","https://openalex.org/W2386865949","https://openalex.org/W2385773603","https://openalex.org/W3111457396","https://openalex.org/W2954309397","https://openalex.org/W2138673725","https://openalex.org/W421912185","https://openalex.org/W2142689953","https://openalex.org/W1562793155"],"abstract_inverted_index":{"Abstract":[0],"By":[1],"means":[2],"of":[3,11,26,87,123,168,198,243],"spatial":[4],"clustering":[5],"and":[6,14,54,99,246],"time-frequency":[7],"masking,":[8],"a":[9,27,31,76,88,181],"mixture":[10,36,47,160],"multiple":[12],"speakers":[13],"noise":[15],"can":[16,39,72],"be":[17,40,67,73,82,217],"separated":[18],"into":[19],"the":[20,44,70,97,105,144,151,159,190,199,221,225,232,241],"underlying":[21],"signal":[22,46],"components.":[23],"The":[24,91,185],"parameters":[25],"model,":[28],"such":[29],"as":[30,58,178,180],"complex":[32],"angular":[33],"central":[34],"Gaussian":[35],"model":[37],"(cACGMM),":[38],"determined":[41],"based":[42,207],"on":[43,208],"given":[45],"itself.":[48],"Then,":[49],"no":[50],"misfit":[51],"between":[52],"training":[53],"testing":[55],"conditions":[56,245],"arises,":[57],"opposed":[59],"to":[60,66,84,96,103,117,149,164,195,216,220],"approaches":[61],"that":[62,188,231],"require":[63],"labeled":[64],"datasets":[65],"trained.":[68],"Whereas":[69],"separation":[71,236],"performed":[74],"in":[75,147,240],"completely":[77],"unsupervised":[78],"way,":[79],"it":[80,100],"may":[81],"beneficial":[83,219],"take":[85],"advantage":[86],"priori":[89],"knowledge.":[90],"parameter":[92],"estimation":[93,249],"is":[94,101,193],"sensitive":[95],"initialization,":[98],"necessary":[102],"address":[104],"frequency":[106],"permutation":[107,222],"problem.":[108],"In":[109,202],"this":[110,203],"paper,":[111],"we":[112,128,137,154,228],"therefore":[113],"consider":[114],"three":[115],"techniques":[116],"overcome":[118,196],"these":[119],"limitations":[120],"using":[121],"direction":[122],"arrival":[124],"(DOA)":[125],"estimates.":[126],"First,":[127],"propose":[129],"an":[130,156],"initialization":[131,192],"with":[132,174],"simple":[133],"DOA-based":[134,191],"masks.":[135],"Secondly,":[136],"derive":[138],"speaker":[139],"specific":[140,163],"time":[141],"annotations":[142],"from":[143],"same":[145],"masks":[146],"order":[148],"constrain":[150],"cACGMM.":[152],"Thirdly,":[153],"employ":[155],"approach":[157],"where":[158],"components":[161],"are":[162,213],"each":[165,169],"DOA":[166,176,248],"instead":[167],"speaker.":[170,184],"We":[171],"conduct":[172],"experiments":[173],"sudden":[175],"changes,":[177],"well":[179],"gradually":[182],"moving":[183],"results":[186],"demonstrate":[187],"particularly":[189],"effective":[194],"both":[197],"described":[200],"limitations.":[201],"case,":[204],"even":[205],"methods":[206],"normally":[209],"unavailable":[210],"oracle":[211],"information":[212],"not":[214],"observed":[215],"more":[218],"resolution":[223],"or":[224],"initialization.":[226],"Lastly,":[227],"also":[229],"show":[230],"proposed":[233],"DOA-guided":[234],"source":[235],"works":[237],"quite":[238],"robustly":[239],"presence":[242],"adverse":[244],"realistic":[247],"errors.":[250]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}