{"id":"https://openalex.org/W4205259838","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660526","title":"Towards the Development of Segment Level Speech Overlap Detection Using Convolutional Neural Network","display_name":"Towards the Development of Segment Level Speech Overlap Detection Using Convolutional Neural Network","publication_year":2021,"publication_date":"2021-11-18","ids":{"openalex":"https://openalex.org/W4205259838","doi":"https://doi.org/10.1109/o-cocosda202152914.2021.9660526"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda202152914.2021.9660526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5048204946","display_name":"Ronald John Cabatic","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090490","display_name":"National University","ror":"https://ror.org/000a8qk84","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210090490"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Ronald John O. Cabatic","raw_affiliation_strings":["College of Computing and Information Technologies, National University, Manila, Manila, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Information Technologies, National University, Manila, Manila, Philippines","institution_ids":["https://openalex.org/I4210090490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069976462","display_name":"Angelica De La Cruz","orcid":"https://orcid.org/0000-0003-4347-6079"},"institutions":[{"id":"https://openalex.org/I4210090490","display_name":"National University","ror":"https://ror.org/000a8qk84","country_code":"PH","type":"education","lineage":["https://openalex.org/I4210090490"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"Angelica H. De La Cruz","raw_affiliation_strings":["College of Computing and Information Technologies, National University, Manila, Manila, Philippines"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Information Technologies, National University, Manila, Manila, Philippines","institution_ids":["https://openalex.org/I4210090490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090490"],"apc_list":null,"apc_paid":null,"fwci":0.1365,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57286835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"68","issue":null,"first_page":"65","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7916640043258667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544428110122681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6318077445030212},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47213107347488403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45605987310409546}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7916640043258667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544428110122681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6318077445030212},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47213107347488403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45605987310409546}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda202152914.2021.9660526","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda202152914.2021.9660526","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 24th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2095705004","https://openalex.org/W2114970513","https://openalex.org/W2402428045","https://openalex.org/W2509595571","https://openalex.org/W2611199340","https://openalex.org/W2787931417","https://openalex.org/W2904803562","https://openalex.org/W2962734882","https://openalex.org/W2968071640","https://openalex.org/W3045742579","https://openalex.org/W3094892544","https://openalex.org/W6674330103","https://openalex.org/W6766953758"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"There":[0],"are":[1],"various":[2],"factors":[3],"that":[4,49],"affects":[5],"the":[6,18,36,61,98,101,104,109,119,126],"performance":[7,62],"of":[8,15,20,38,45,63,66,103,133,147],"a":[9,26,39],"speech":[10,54,76,142,149],"processing":[11],"system":[12],"and":[13,93,106,135],"one":[14,32],"these":[16],"is":[17,43,87,114],"presence":[19],"overlapped":[21,53,75,148],"speech.":[22],"It":[23],"occurs":[24],"when":[25],"certain":[27],"segment":[28,56],"contains":[29],"more":[30],"than":[31],"speaker,":[33],"thus":[34],"altering":[35],"information":[37],"segment.":[40],"This":[41,58],"study":[42],"part":[44],"an":[46,131],"ongoing":[47],"research":[48],"aims":[50],"to":[51],"detect":[52],"on":[55],"level.":[57],"paper":[59],"presents":[60],"two":[64],"variations":[65],"convolutional":[67],"neural":[68],"network":[69],"(CNN)":[70],"models":[71],"for":[72,91,95,144],"frame":[73],"level":[74],"detection":[77,146],"using":[78],"Augmented":[79],"Multi-party":[80],"Interaction":[81],"(AMI)":[82],"ES2002a":[83],"corpus.":[84],"The":[85],"dataset":[86],"split":[88],"into":[89],"70%":[90],"training":[92],"30%":[94],"testing.":[96],"In":[97],"experiments":[99],"performed,":[100],"fluctuation":[102],"loss":[105],"accuracy":[107,132],"during":[108],"modified":[110],"CNN":[111,121,128],"model":[112,122,129],"development":[113],"not":[115],"as":[116,118],"stable":[117],"conventional":[120,127],"but":[123],"it":[124],"outperformed":[125],"with":[130],"87.02%":[134],"86.18%":[136],"respectively.":[137],"For":[138],"future":[139],"works,":[140],"other":[141],"features":[143],"segment-wise":[145],"will":[150],"be":[151],"explored.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}