{"id":"https://openalex.org/W3015894695","doi":"https://doi.org/10.1109/icassp40776.2020.9054754","title":"Exploiting Periodicity Features for Joint Detection and DOA Estimation of Speech Sources Using Convolutional Neural Networks","display_name":"Exploiting Periodicity Features for Joint Detection and DOA Estimation of Speech Sources Using Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015894695","doi":"https://doi.org/10.1109/icassp40776.2020.9054754","mag":"3015894695"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5074678647","display_name":"Reza Varzandeh","orcid":"https://orcid.org/0009-0009-0076-2148"},"institutions":[{"id":"https://openalex.org/I4210108766","display_name":"Klinikum Oldenburg","ror":"https://ror.org/01t0n2c80","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210108766"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Reza Varzandeh","raw_affiliation_strings":["H\u00f6rTech gGmbH, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"H\u00f6rTech gGmbH, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210108766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010480213","display_name":"Kamil Adilo\u011flu","orcid":"https://orcid.org/0000-0003-0172-8485"},"institutions":[{"id":"https://openalex.org/I4210108766","display_name":"Klinikum Oldenburg","ror":"https://ror.org/01t0n2c80","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210108766"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kamil Adiloglu","raw_affiliation_strings":["H\u00f6rTech gGmbH, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"H\u00f6rTech gGmbH, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210108766"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["Department of Medical Physics and Acoustics, University of Oldenburg"],"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics, University of Oldenburg","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002002386","display_name":"Volker Hohmann","orcid":"https://orcid.org/0000-0001-7056-1880"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Hohmann","raw_affiliation_strings":["Department of Medical Physics and Acoustics, University of Oldenburg"],"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics, University of Oldenburg","institution_ids":["https://openalex.org/I129877168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5074678647"],"corresponding_institution_ids":["https://openalex.org/I4210108766"],"apc_list":null,"apc_paid":null,"fwci":2.2813,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88699902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"566","last_page":"570"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7950708866119385},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7189645171165466},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.6861661672592163},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6675246953964233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6171374917030334},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6017094254493713},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5696272850036621},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5525264739990234},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5410363674163818},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.49222007393836975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44772014021873474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7950708866119385},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7189645171165466},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.6861661672592163},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6675246953964233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6171374917030334},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6017094254493713},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5696272850036621},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5525264739990234},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5410363674163818},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.49222007393836975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44772014021873474},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1515932869","https://openalex.org/W1988272246","https://openalex.org/W2009649672","https://openalex.org/W2046317813","https://openalex.org/W2052666245","https://openalex.org/W2095425552","https://openalex.org/W2113416157","https://openalex.org/W2113638573","https://openalex.org/W2121165908","https://openalex.org/W2174451236","https://openalex.org/W2181253919","https://openalex.org/W2259750646","https://openalex.org/W2623647742","https://openalex.org/W2747306262","https://openalex.org/W2772736377","https://openalex.org/W2773382844","https://openalex.org/W2810934215","https://openalex.org/W2884424734","https://openalex.org/W2885219692","https://openalex.org/W2900006343","https://openalex.org/W2903098622","https://openalex.org/W2945339796","https://openalex.org/W2962708126","https://openalex.org/W3101162615","https://openalex.org/W3105684258","https://openalex.org/W3127686677","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2766995619","https://openalex.org/W4224270619","https://openalex.org/W2579722767","https://openalex.org/W2168148781","https://openalex.org/W2026165661","https://openalex.org/W1991848873","https://openalex.org/W2593008828","https://openalex.org/W2099651033","https://openalex.org/W2155323221","https://openalex.org/W2949200214"],"abstract_inverted_index":{"While":[0],"many":[1],"algorithms":[2],"deal":[3],"with":[4,71],"direction":[5],"of":[6,23,59,91,95,148],"arrival":[7],"(DOA)":[8],"estimation":[9,53,150],"and":[10,54,170],"voice":[11],"activity":[12],"detection":[13],"(VAD)":[14],"as":[15],"two":[16,29],"separate":[17],"tasks,":[18],"only":[19],"a":[20,35,46,88,105,116],"small":[21],"number":[22],"data-driven":[24],"methods":[25],"have":[26],"addressed":[27],"these":[28],"tasks":[30],"jointly.":[31],"In":[32,63,152],"this":[33],"paper,":[34],"multi-input":[36],"single-output":[37],"convolutional":[38],"neural":[39],"network":[40,77],"(CNN)":[41],"is":[42,132,161],"proposed":[43,99,130,159],"which":[44,86],"exploits":[45],"novel":[47],"feature":[48,81],"combination":[49],"for":[50,115],"joint":[51],"DOA":[52,149],"VAD":[55],"in":[56,104,119,146],"the":[57,66,76,92,96,126,129,143,154,158],"context":[58],"binaural":[60],"hearing":[61],"aids.":[62],"addition":[64],"to":[65,134,163,165],"well-known":[67],"generalized":[68],"cross":[69],"correlation":[70],"phase":[72],"transform":[73],"(GCC-PHAT)":[74],"feature,":[75,128],"uses":[78],"an":[79],"auditory-inspired":[80],"called":[82],"periodicity":[83],"degree":[84],"(PD),":[85],"provides":[87],"broadband":[89],"representation":[90],"periodic":[93],"structure":[94],"signal.":[97],"The":[98],"CNN":[100,131,145],"has":[101],"been":[102],"trained":[103],"multi-conditional":[106],"training":[107],"scheme":[108],"across":[109],"different":[110,166],"signal-to-noise":[111],"ratios.":[112],"Experimental":[113],"results":[114,155],"single-talker":[117],"scenario":[118],"reverberant":[120],"environments":[121],"show":[122,156],"that":[123,157],"by":[124],"exploiting":[125],"PD":[127],"able":[133,162],"distinguish":[135],"speech":[136],"from":[137],"non-speech":[138],"signal":[139],"blocks,":[140],"thereby":[141],"outperforming":[142],"baseline":[144],"terms":[147],"accuracy.":[151],"addition,":[153],"method":[160],"adapt":[164],"unseen":[167],"acoustic":[168],"conditions":[169],"background":[171],"noises.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}