{"id":"https://openalex.org/W3038713101","doi":"https://doi.org/10.1109/percom45495.2020.9127390","title":"Speaker Counting Model based on Transfer Learning from SincNet Bottleneck Layer","display_name":"Speaker Counting Model based on Transfer Learning from SincNet Bottleneck Layer","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3038713101","doi":"https://doi.org/10.1109/percom45495.2020.9127390","mag":"3038713101"},"language":"en","primary_location":{"id":"doi:10.1109/percom45495.2020.9127390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/percom45495.2020.9127390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Pervasive Computing and Communications (PerCom)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.utwente.nl/en/publications/7cebfff6-2435-4dc0-b4db-2e1ce7bdfbd8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100391971","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-4392-1884"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Pervasive Systems Group, University of Twente, Enschede, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Pervasive Systems Group, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048115167","display_name":"Fatjon Seraj","orcid":"https://orcid.org/0000-0002-2711-0774"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Fatjon Seraj","raw_affiliation_strings":["Pervasive Systems Group, University of Twente, Enschede, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Pervasive Systems Group, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003885813","display_name":"Nirvana Meratnia","orcid":"https://orcid.org/0000-0002-8379-770X"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nirvana Meratnia","raw_affiliation_strings":["Pervasive Systems Group, University of Twente, Enschede, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Pervasive Systems Group, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067566830","display_name":"Paul Havinga","orcid":"https://orcid.org/0000-0002-3399-1790"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Paul J.M. Havinga","raw_affiliation_strings":["Pervasive Systems Group, University of Twente, Enschede, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Pervasive Systems Group, University of Twente, Enschede, The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100391971"],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":1.9771,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86875204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2020","issue":null,"first_page":"1","last_page":"8"},"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":0.9993000030517578,"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":0.9990000128746033,"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":0.8014342784881592},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.7746887803077698},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6587284207344055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.591779887676239},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5477931499481201},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5141911506652832},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45885518193244934},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.44915691018104553},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.42478734254837036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4064965546131134},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.1965560019016266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014342784881592},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7746887803077698},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6587284207344055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.591779887676239},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5477931499481201},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5141911506652832},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45885518193244934},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.44915691018104553},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.42478734254837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064965546131134},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.1965560019016266},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/percom45495.2020.9127390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/percom45495.2020.9127390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Pervasive Computing and Communications (PerCom)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire/7cebfff6-2435-4dc0-b4db-2e1ce7bdfbd8","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/7cebfff6-2435-4dc0-b4db-2e1ce7bdfbd8","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wang, W, Seraj, F, Meratnia, N & Havinga, P J M 2020, Speaker Counting Model based on Transfer Learning from SincNet Bottleneck Layer. in 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom)., 9127390, Annual IEEE International Conference on Pervasive Computing and Communications (PerCom), vol. 2020, IEEE, pp. 1, 2020 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom 2020, Austin, Texas, United States, 23/03/20. https://doi.org/10.1109/PerCom45495.2020.9127390","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:ris.utwente.nl:publications/7cebfff6-2435-4dc0-b4db-2e1ce7bdfbd8","is_oa":false,"landing_page_url":"http://www.scopus.com/inward/record.url?scp=85088690998&partnerID=8YFLogxK","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"","raw_type":""},{"id":"mag:3159489771","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002268990130088","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:ris.utwente.nl:openaire/7cebfff6-2435-4dc0-b4db-2e1ce7bdfbd8","is_oa":true,"landing_page_url":"https://research.utwente.nl/en/publications/7cebfff6-2435-4dc0-b4db-2e1ce7bdfbd8","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Wang, W, Seraj, F, Meratnia, N & Havinga, P J M 2020, Speaker Counting Model based on Transfer Learning from SincNet Bottleneck Layer. in 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom)., 9127390, Annual IEEE International Conference on Pervasive Computing and Communications (PerCom), vol. 2020, IEEE, pp. 1, 2020 IEEE International Conference on Pervasive Computing and Communications Workshops, PerCom 2020, Austin, Texas, United States, 23/03/20. https://doi.org/10.1109/PerCom45495.2020.9127390","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W186826960","https://openalex.org/W1494198834","https://openalex.org/W1552056348","https://openalex.org/W1605972624","https://openalex.org/W1989115430","https://openalex.org/W1995921382","https://openalex.org/W2029880715","https://openalex.org/W2045956438","https://openalex.org/W2060300932","https://openalex.org/W2088358148","https://openalex.org/W2096173716","https://openalex.org/W2115175902","https://openalex.org/W2123175289","https://openalex.org/W2138761758","https://openalex.org/W2145276819","https://openalex.org/W2150769028","https://openalex.org/W2155776568","https://openalex.org/W2165880886","https://openalex.org/W2171679232","https://openalex.org/W2187089797","https://openalex.org/W2253429366","https://openalex.org/W2773082988","https://openalex.org/W2964052309","https://openalex.org/W3210163254","https://openalex.org/W6681613270"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2748922771"],"abstract_inverted_index":{"People":[0],"counting":[1,56,102,120],"techniques":[2],"have":[3],"been":[4],"widely":[5],"researched":[6],"recently":[7],"and":[8,64,89,143,183],"many":[9],"different":[10],"types":[11],"of":[12,37,112,157],"sensors":[13],"can":[14],"be":[15,141],"used":[16],"in":[17,39,59,96,104,122,146],"this":[18,21,84],"context.":[19],"In":[20,47,100],"paper,":[22],"we":[23,168],"propose":[24],"a":[25,29,48,123,170],"system":[26,51,85],"based":[27],"on":[28,53,179],"deep-learning":[30],"model":[31,159,167],"able":[32],"to":[33,73,92,140,163],"identify":[34],"the":[35,40,44,50,93,97,109,119,130,154,180],"number":[36,111],"people":[38],"crowded":[41,98],"scenarios":[42],"through":[43],"speech":[45],"sound.":[46],"nutshell":[49],"relies":[52],"two":[54],"components:":[55],"concurrent":[57],"speakers":[58,103,113],"overlapping":[60,94,105],"talking":[61],"sound":[62,67,95,106,147],"directly":[63],"clustering":[65,166],"single-speaker":[66,82],"by":[68,129],"speaker-identity":[69],"over":[70],"time.":[71],"Compared":[72],"previously":[74],"proposed":[75,132],"speaker-counting":[76],"systems":[77],"models":[78,176],"that":[79,115],"only":[80],"cluster":[81],"sound,":[83],"is":[86,127],"more":[87],"accurate":[88],"less":[90],"vulnerable":[91],"environment.":[99],"addition,":[101],"also":[107,117],"gives":[108],"minimal":[110],"so":[114],"it":[116],"improves":[118],"accuracy":[121],"quiet":[124],"environment.Our":[125],"methodology":[126],"inspired":[128],"newly":[131],"SincNet":[133,158],"deep":[134],"neural":[135],"network":[136],"framework":[137],"which":[138],"proves":[139],"outstanding":[142],"highly":[144],"efficient":[145],"processing":[148],"with":[149],"raw":[150],"signals.":[151],"By":[152],"transferring":[153],"bottleneck":[155],"layer":[156],"as":[160],"features":[161],"fed":[162],"our":[164],"speaker":[165],"reached":[169],"noticeably":[171],"better":[172],"performance":[173],"than":[174],"previous":[175],"who":[177],"rely":[178],"use":[181],"MFCC":[182],"other":[184],"engineered":[185],"features.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}