{"id":"https://openalex.org/W2787726203","doi":"https://doi.org/10.1109/apsipa.2017.8282303","title":"Blind speaker counting in highly reverberant environments by clustering coherence features","display_name":"Blind speaker counting in highly reverberant environments by clustering coherence features","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787726203","doi":"https://doi.org/10.1109/apsipa.2017.8282303","mag":"2787726203"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007769118","display_name":"Shahab Pasha","orcid":"https://orcid.org/0000-0002-6805-166X"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Shahab Pasha","raw_affiliation_strings":["Computer and Telecommunication Engineering, University of Wollongong, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Computer and Telecommunication Engineering, University of Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055065049","display_name":"Jacob Donley","orcid":"https://orcid.org/0000-0002-8401-798X"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jacob Donley","raw_affiliation_strings":["Computer and Telecommunication Engineering, University of Wollongong, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Computer and Telecommunication Engineering, University of Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033818201","display_name":"Christian Ritz","orcid":"https://orcid.org/0000-0002-3768-7569"},"institutions":[{"id":"https://openalex.org/I204824540","display_name":"University of Wollongong","ror":"https://ror.org/00jtmb277","country_code":"AU","type":"education","lineage":["https://openalex.org/I204824540"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Christian Ritz","raw_affiliation_strings":["Computer and Telecommunication Engineering, University of Wollongong, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"Computer and Telecommunication Engineering, University of Wollongong, NSW, Australia","institution_ids":["https://openalex.org/I204824540"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5007769118"],"corresponding_institution_ids":["https://openalex.org/I204824540"],"apc_list":null,"apc_paid":null,"fwci":0.7457,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.73455907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1684","last_page":"1687"},"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":0.9980000257492065,"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":0.9943000078201294,"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/reverberation","display_name":"Reverberation","score":0.7522321343421936},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7250866889953613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7117372155189514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7016228437423706},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6899616718292236},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6665510535240173},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5049284100532532},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41520172357559204},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4145495593547821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41218721866607666},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40424904227256775},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.40125057101249695},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15241029858589172},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11055320501327515},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10711923241615295},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0677340030670166},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06243252754211426}],"concepts":[{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7522321343421936},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7250866889953613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117372155189514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7016228437423706},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6899616718292236},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6665510535240173},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5049284100532532},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41520172357559204},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4145495593547821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41218721866607666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40424904227256775},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.40125057101249695},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15241029858589172},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11055320501327515},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10711923241615295},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0677340030670166},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06243252754211426},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/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/apsipa.2017.8282303","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282303","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:ro.uow.edu.au:eispapers1-2699","is_oa":false,"landing_page_url":"https://ro.uow.edu.au/eispapers1/1697","pdf_url":null,"source":{"id":"https://openalex.org/S4306400510","display_name":"Research Online (University of Wollongong)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I204824540","host_organization_name":"University of Wollongong","host_organization_lineage":["https://openalex.org/I204824540"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty of Engineering and Information Sciences - Papers: Part B","raw_type":"presentation"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1485666612","https://openalex.org/W1893064206","https://openalex.org/W1969299255","https://openalex.org/W1991899119","https://openalex.org/W2046317813","https://openalex.org/W2049919499","https://openalex.org/W2055012008","https://openalex.org/W2059857061","https://openalex.org/W2108323654","https://openalex.org/W2109689830","https://openalex.org/W2114863372","https://openalex.org/W2119979862","https://openalex.org/W2137178960","https://openalex.org/W2147143627","https://openalex.org/W2158216966","https://openalex.org/W2158855478","https://openalex.org/W2166547995","https://openalex.org/W2167689159","https://openalex.org/W2291939856","https://openalex.org/W2314859257","https://openalex.org/W2399221843","https://openalex.org/W2578016082","https://openalex.org/W2606147034","https://openalex.org/W3124056356","https://openalex.org/W6681645738"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2331622705","https://openalex.org/W2391832549","https://openalex.org/W4401069787","https://openalex.org/W1562475690","https://openalex.org/W1488529827"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"the":[3,6,44,55,58,66,71,82,89],"use":[4],"of":[5,18,43,70,110],"frequency-":[7],"domain":[8,68,84],"Magnitude":[9],"Squared":[10],"Coherence":[11],"(MSC)":[12],"between":[13,54],"two":[14],"ad-":[15],"hoc":[16],"recordings":[17],"speech":[19,72],"as":[20],"a":[21],"reliable":[22],"speaker":[23],"discrimination":[24],"feature":[25],"for":[26,101,107],"source":[27,36,98],"counting":[28,37,61,99],"applications":[29],"in":[30],"highly":[31,96],"reverberant":[32],"environments.":[33],"The":[34],"proposed":[35],"method":[38,90],"does":[39,48],"not":[40,49],"require":[41],"knowledge":[42],"microphone":[45,113],"spacing":[46],"and":[47,57,88,112],"assume":[50],"any":[51],"relative":[52],"distance":[53],"sources":[56],"microphones.":[59],"Source":[60],"is":[62,86],"based":[63],"on":[64],"clustering":[65],"frequency":[67,83],"MSC":[69,85],"signals":[73],"derived":[74],"from":[75],"short":[76],"time":[77],"segments.":[78],"Experiments":[79],"show":[80],"that":[81],"speaker-dependent":[87],"was":[91],"successfully":[92],"used":[93],"to":[94,103],"obtain":[95],"accurate":[97],"results":[100],"up":[102],"six":[104],"active":[105],"speakers":[106],"varying":[108],"levels":[109],"reverberation":[111],"spacing.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}