{"id":"https://openalex.org/W4402351868","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650377","title":"Dual-Stage Training Frame-level Overlapping Speech Detection Model Based on Convolutional Neural Network Architecture","display_name":"Dual-Stage Training Frame-level Overlapping Speech Detection Model Based on Convolutional Neural Network Architecture","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351868","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650377"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650377","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101335551","display_name":"Zhifei Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifei Pan","raw_affiliation_strings":["Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066672771","display_name":"Guangcun Wei","orcid":"https://orcid.org/0009-0003-6428-7696"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangcun Wei","raw_affiliation_strings":["Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108318108","display_name":"Qingge Fang","orcid":"https://orcid.org/0009-0003-5799-1888"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingge Fang","raw_affiliation_strings":["Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046415570","display_name":"Jihua Fu","orcid":"https://orcid.org/0009-0004-4784-2691"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Fu","raw_affiliation_strings":["Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100637677","display_name":"Jianan Liu","orcid":"https://orcid.org/0009-0002-7179-0129"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianan Liu","raw_affiliation_strings":["Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University of Science and Technology,School of Intelligent Equipment,Tai’an,China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14658495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.996999979019165,"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":0.7912800908088684},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6477823257446289},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6434244513511658},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5618936419487},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.5162448883056641},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5028945803642273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4722660779953003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4539269804954529},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41581201553344727},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3216695189476013},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11703094840049744}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7912800908088684},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6477823257446289},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6434244513511658},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5618936419487},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.5162448883056641},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5028945803642273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4722660779953003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4539269804954529},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41581201553344727},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3216695189476013},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11703094840049744},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650377","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W191366985","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2402428045","https://openalex.org/W2752782242","https://openalex.org/W2942551338","https://openalex.org/W2943934118","https://openalex.org/W2952752702","https://openalex.org/W2990138404","https://openalex.org/W3015528371","https://openalex.org/W3015780472","https://openalex.org/W3016244460","https://openalex.org/W3045742579","https://openalex.org/W3094892544","https://openalex.org/W3098454764","https://openalex.org/W3157070662","https://openalex.org/W3167976421","https://openalex.org/W3170201991","https://openalex.org/W3198482860","https://openalex.org/W3198827946","https://openalex.org/W3203236698","https://openalex.org/W3207834622","https://openalex.org/W3211278025","https://openalex.org/W3212886388","https://openalex.org/W4206908380","https://openalex.org/W4396835595","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4293226380","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611"],"abstract_inverted_index":{"A":[0],"dual-stage":[1],"training":[2],"frame-level":[3],"overlapping":[4,64,111,129],"speech":[5,54,61,65,86,112,130],"detection":[6,131],"model":[7,52,81,94,132],"is":[8,24,95,101],"proposed":[9,128],"in":[10,72],"this":[11],"paper,":[12],"with":[13,103,140],"its":[14],"core":[15],"being":[16],"based":[17],"on":[18,26,136],"RepVGG":[19,23,49,68,98],"blocks":[20,69,99],"structure,":[21],"and":[22,39,63,85,100,110,120],"built":[25],"simple":[27],"one-dimensional":[28],"Convolutional":[29],"Neural":[30],"Networks":[31],"(CNNs).":[32],"Both":[33],"the":[34,48,73,137],"learning":[35],"of":[36,42,75],"local":[37],"features":[38,41],"temporal":[40],"acoustic":[43],"signals":[44],"are":[45,70,118],"accomplished":[46],"by":[47],"structure.":[50],"The":[51,127],"categorizes":[53],"into":[55],"triple":[56],"classes:":[57],"non-speech":[58,84],"frames,":[59,62],"non-overlapping":[60,109],"frames.":[66,87,113],"Firstly,":[67],"employed":[71],"construction":[74],"a":[76,89],"Speech":[77,91],"Activity":[78],"Detection":[79,92],"(SAD)":[80],"to":[82,106,122],"detect":[83],"Subsequently,":[88],"Overlapping":[90],"(OSD)":[93],"constructed":[96],"using":[97],"trained":[102],"real":[104],"labels":[105],"differentiate":[107],"between":[108],"Finally,":[114],"these":[115],"two":[116],"models":[117],"combined":[119],"fine-tuned":[121],"directly":[123],"output":[124],"classification":[125],"results.":[126],"achieves":[133],"advanced":[134],"performance":[135],"AliMeeting":[138],"dataset":[139],"fewer":[141],"parameters.":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}