{"id":"https://openalex.org/W2898395910","doi":"https://doi.org/10.1109/taslp.2018.2877892","title":"CountNet: Estimating the Number of Concurrent Speakers Using Supervised Learning","display_name":"CountNet: Estimating the Number of Concurrent Speakers Using Supervised Learning","publication_year":2018,"publication_date":"2018-10-24","ids":{"openalex":"https://openalex.org/W2898395910","doi":"https://doi.org/10.1109/taslp.2018.2877892","mag":"2898395910"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2877892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2877892","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-02010805","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051066378","display_name":"Fabian-Robert St\u00f6ter","orcid":"https://orcid.org/0000-0002-2534-1165"},"institutions":[{"id":"https://openalex.org/I4210101743","display_name":"Laboratoire d'Informatique, de Robotique et de Micro\u00e9lectronique de Montpellier","ror":"https://ror.org/013yean28","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I151295451","https://openalex.org/I19894307","https://openalex.org/I4210101743","https://openalex.org/I4210159245","https://openalex.org/I4405261681"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabian-Robert Stoter","raw_affiliation_strings":["Inria, LIRMM, Montpellier, France"],"raw_orcid":"https://orcid.org/0000-0002-2534-1165","affiliations":[{"raw_affiliation_string":"Inria, LIRMM, Montpellier, France","institution_ids":["https://openalex.org/I4210101743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047247941","display_name":"Soumitro Chakrabarty","orcid":"https://orcid.org/0000-0002-0846-207X"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Soumitro Chakrabarty","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0846-207X","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022331149","display_name":"Bernd Edler","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Edler","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanuel A. P. Habets","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2613-8046","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2646,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.95322148,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"27","issue":"2","first_page":"268","last_page":"282"},"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":0.9998000264167786,"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":0.8189423084259033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6477892994880676},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6023551225662231},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5606666207313538},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5059482455253601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49048230051994324},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4724576771259308},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4724448323249817},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45502668619155884},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4530293047428131},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.43703144788742065},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.41329145431518555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4004763960838318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08395686745643616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8189423084259033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6477892994880676},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6023551225662231},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5606666207313538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5059482455253601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49048230051994324},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4724576771259308},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4724448323249817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45502668619155884},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4530293047428131},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.43703144788742065},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.41329145431518555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4004763960838318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08395686745643616},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2018.2877892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2877892","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:lirmm-02010805v1","is_oa":true,"landing_page_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-02010805","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27 (2), pp.268-282. ⟨10.1109/TASLP.2018.2877892⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:fraunhofer.de:N-590254","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-590254.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IIS","raw_type":"Journal Article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/262723","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/262723","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:HAL:lirmm-02010805v1","is_oa":true,"landing_page_url":"https://hal-lirmm.ccsd.cnrs.fr/lirmm-02010805","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27 (2), pp.268-282. ⟨10.1109/TASLP.2018.2877892⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":104,"referenced_works":["https://openalex.org/W43416829","https://openalex.org/W72302491","https://openalex.org/W299254312","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1580006876","https://openalex.org/W1583001605","https://openalex.org/W1589339348","https://openalex.org/W1594771616","https://openalex.org/W1600744878","https://openalex.org/W1605972624","https://openalex.org/W1686810756","https://openalex.org/W1860246075","https://openalex.org/W1907657117","https://openalex.org/W1909455558","https://openalex.org/W1910776219","https://openalex.org/W1954873805","https://openalex.org/W1964538581","https://openalex.org/W1966364906","https://openalex.org/W1978232622","https://openalex.org/W1988520084","https://openalex.org/W2003266707","https://openalex.org/W2010114458","https://openalex.org/W2016882596","https://openalex.org/W2029880715","https://openalex.org/W2059652044","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2069143585","https://openalex.org/W2081045838","https://openalex.org/W2081074144","https://openalex.org/W2085464278","https://openalex.org/W2106411961","https://openalex.org/W2113154266","https://openalex.org/W2117678320","https://openalex.org/W2123045220","https://openalex.org/W2124906580","https://openalex.org/W2125833791","https://openalex.org/W2129191002","https://openalex.org/W2149457037","https://openalex.org/W2151572725","https://openalex.org/W2160779631","https://openalex.org/W2160815625","https://openalex.org/W2167689159","https://openalex.org/W2171679232","https://openalex.org/W2193413348","https://openalex.org/W2221409856","https://openalex.org/W2264443218","https://openalex.org/W2284628133","https://openalex.org/W2399934308","https://openalex.org/W2401494929","https://openalex.org/W2402428045","https://openalex.org/W2406060094","https://openalex.org/W2406222150","https://openalex.org/W2437181147","https://openalex.org/W2460742184","https://openalex.org/W2511082734","https://openalex.org/W2517615595","https://openalex.org/W2519965060","https://openalex.org/W2541389513","https://openalex.org/W2566935005","https://openalex.org/W2575145750","https://openalex.org/W2578538565","https://openalex.org/W2591013610","https://openalex.org/W2591682631","https://openalex.org/W2604509013","https://openalex.org/W2605138598","https://openalex.org/W2626961305","https://openalex.org/W2638067502","https://openalex.org/W2745338770","https://openalex.org/W2746241180","https://openalex.org/W2773082988","https://openalex.org/W2775505379","https://openalex.org/W2787726203","https://openalex.org/W2962683745","https://openalex.org/W2962851944","https://openalex.org/W2963451564","https://openalex.org/W2963686699","https://openalex.org/W2963717945","https://openalex.org/W4245862033","https://openalex.org/W4247480362","https://openalex.org/W4256735665","https://openalex.org/W6601722059","https://openalex.org/W6602944679","https://openalex.org/W6610533790","https://openalex.org/W6631190155","https://openalex.org/W6635144179","https://openalex.org/W6637373629","https://openalex.org/W6638934612","https://openalex.org/W6676179485","https://openalex.org/W6677995690","https://openalex.org/W6685133223","https://openalex.org/W6687566353","https://openalex.org/W6695553435","https://openalex.org/W6712646226","https://openalex.org/W6713312292","https://openalex.org/W6713723810","https://openalex.org/W6726944409","https://openalex.org/W6727040340","https://openalex.org/W6739192308","https://openalex.org/W6743236006","https://openalex.org/W6743401195","https://openalex.org/W6747331233","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2037265366","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3008584592","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Estimating":[0],"the":[1,91,148,157,183],"maximum":[2],"number":[3],"of":[4,93,124,159,169],"concurrent":[5],"speakers":[6],"from":[7],"single-channel":[8],"mixtures":[9],"is":[10,173],"a":[11,36,111,135],"challenging":[12],"problem":[13],"and":[14,31,70,76,165],"an":[15],"essential":[16],"first":[17],"step":[18],"to":[19,47,58,131,151,175],"address":[20],"various":[21],"audio-based":[22],"tasks":[23],"such":[24,64],"as":[25,154,156],"blind":[26],"source":[27],"separation,":[28],"speaker":[29,94],"diarization,":[30],"audio":[32],"surveillance.":[33],"We":[34],"propose":[35],"unifying":[37],"probabilistic":[38],"paradigm,":[39],"where":[40],"deep":[41,85],"neural":[42,104],"network":[43],"architectures":[44,65,86],"are":[45,54,118],"used":[46,109,185],"infer":[48],"output":[49,168],"posterior":[50],"distributions.":[51],"These":[52],"probabilities":[53],"in":[55,84,110],"turn":[56],"processed":[57],"yield":[59],"discrete":[60],"point":[61],"estimates.":[62],"Designing":[63],"often":[66],"involves":[67],"two":[68],"important":[69],"complementary":[71],"aspects":[72],"that":[73,101],"we":[74,79,99,127,146,179],"investigate":[75],"discuss.":[77],"First,":[78],"study":[80,113],"how":[81],"recent":[82],"advances":[83],"may":[87],"be":[88],"exploited":[89],"for":[90,121],"task":[92],"count":[95],"estimation.":[96],"In":[97],"particular,":[98],"show":[100],"convolutional":[102],"recurrent":[103,107],"networks":[105,108],"outperform":[106],"previous":[112],"when":[114],"adequate":[115],"input":[116],"features":[117],"used.":[119],"Even":[120],"short":[122],"segments":[123],"speech":[125],"mixtures,":[126],"can":[128],"estimate":[129],"up":[130],"five":[132],"speakers,":[133],"with":[134],"significantly":[136],"lower":[137],"error":[138],"than":[139],"other":[140],"methods.":[141],"Second,":[142],"through":[143],"comprehensive":[144],"evaluation,":[145],"compare":[147],"best-performing":[149],"method":[150,172],"several":[152],"baselines,":[153],"well":[155],"influence":[158],"gain":[160],"variations,":[161],"different":[162],"data":[163],"sets,":[164],"reverberation.":[166],"The":[167],"our":[170,187],"proposed":[171,188],"compared":[174],"human":[176],"performance.":[177],"Finally,":[178],"give":[180],"insights":[181],"into":[182],"strategy":[184],"by":[186],"method.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}