{"id":"https://openalex.org/W3108855822","doi":"https://doi.org/10.1145/3400286.3418270","title":"Data Augmentation and D-vector Representation Methods for Speaker Change Detection","display_name":"Data Augmentation and D-vector Representation Methods for Speaker Change Detection","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3108855822","doi":"https://doi.org/10.1145/3400286.3418270","mag":"3108855822"},"language":"en","primary_location":{"id":"doi:10.1145/3400286.3418270","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3400286.3418270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","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/A5100727942","display_name":"Ji\u2010Su Park","orcid":"https://orcid.org/0000-0001-7113-4792"},"institutions":[{"id":"https://openalex.org/I112728665","display_name":"Hannam University","ror":"https://ror.org/01cwbae71","country_code":"KR","type":"education","lineage":["https://openalex.org/I112728665"]},{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisu Park","raw_affiliation_strings":["ETRI, Yuseong-gu, Daejeon Republic of Korea","Hannam University, Daedeok-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI, Yuseong-gu, Daejeon Republic of Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Hannam University, Daedeok-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I112728665"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018792328","display_name":"Shin Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I112728665","display_name":"Hannam University","ror":"https://ror.org/01cwbae71","country_code":"KR","type":"education","lineage":["https://openalex.org/I112728665"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shin Cha","raw_affiliation_strings":["Hannam University, Daedeok-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hannam University, Daedeok-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I112728665"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110749311","display_name":"Seongbae Eun","orcid":null},"institutions":[{"id":"https://openalex.org/I112728665","display_name":"Hannam University","ror":"https://ror.org/01cwbae71","country_code":"KR","type":"education","lineage":["https://openalex.org/I112728665"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongbae Eun","raw_affiliation_strings":["Hannam University, Daedeok-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hannam University, Daedeok-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I112728665"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009820747","display_name":"Jeon Gue Park","orcid":"https://orcid.org/0000-0002-1499-5542"},"institutions":[{"id":"https://openalex.org/I112728665","display_name":"Hannam University","ror":"https://ror.org/01cwbae71","country_code":"KR","type":"education","lineage":["https://openalex.org/I112728665"]},{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeon Gue Park","raw_affiliation_strings":["ETRI, Yuseong-gu, Daejeon Republic of Korea","Hannam University, Daedeok-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETRI, Yuseong-gu, Daejeon Republic of Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Hannam University, Daedeok-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I112728665"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101941666","display_name":"Young-Sun Yun","orcid":"https://orcid.org/0000-0003-3349-8450"},"institutions":[{"id":"https://openalex.org/I112728665","display_name":"Hannam University","ror":"https://ror.org/01cwbae71","country_code":"KR","type":"education","lineage":["https://openalex.org/I112728665"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Sun Yun","raw_affiliation_strings":["Hannam University, Daedeok-gu, Daejeon, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hannam University, Daedeok-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I112728665"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15348686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9922000169754028,"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":0.9857000112533569,"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":0.7905195951461792},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6618951559066772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6145297884941101},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5861668586730957},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5552260875701904},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5067394375801086},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.489670068025589},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4643006920814514},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4567611515522003},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4467836916446686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34866267442703247},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.34476178884506226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905195951461792},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6618951559066772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6145297884941101},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5861668586730957},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5552260875701904},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5067394375801086},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.489670068025589},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4643006920814514},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4567611515522003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4467836916446686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34866267442703247},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.34476178884506226},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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:10.1145/3400286.3418270","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3400286.3418270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2029687556","https://openalex.org/W2046056978","https://openalex.org/W2074394031","https://openalex.org/W2099333848","https://openalex.org/W2150769028","https://openalex.org/W2288613265","https://openalex.org/W2618760106","https://openalex.org/W2746241180","https://openalex.org/W2746710273","https://openalex.org/W2962788625","https://openalex.org/W2963015630","https://openalex.org/W2963470929","https://openalex.org/W3015783745"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2206035908","https://openalex.org/W2501000458","https://openalex.org/W4247736853","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2162158162","https://openalex.org/W1493012537"],"abstract_inverted_index":{"Speaker":[0],"Change":[1],"Detection":[2],"(SCD)":[3],"is":[4,91,96,140],"the":[5,33,43,51,68,85,88,94,111,130,135,146,155,159,162,183,186,190,198,204],"process":[6],"that":[7],"detects":[8],"speaker":[9,28,40,69],"changes":[10,70],"during":[11],"a":[12,23,39,149],"conversation.":[13],"The":[14,175],"conversation":[15],"can":[16],"be":[17],"divided":[18],"into":[19,142],"homogeneous":[20],"segments":[21,34],"using":[22,72],"typical":[24],"SCD":[25,89,123],"system":[26,30,82,205,209],"or":[27,49,202,215],"diarization":[29],"in":[31,148,154],"which":[32],"are":[35,45,59,77],"partitioned":[36],"according":[37,144],"to":[38,47,63,108,119,145,171,197,206],"identity.":[41],"When":[42],"d-vectors":[44,121],"used":[46],"identify":[48],"verify":[50],"speakers":[52,139],"with":[53],"deep":[54],"neural":[55],"network":[56],"model,":[57],"they":[58],"often":[60],"considered":[61],"insufficient":[62],"train":[64],"model":[65,158],"for":[66,81,110,122],"detecting":[67],"by":[71],"only":[73],"acoustic":[74],"information.":[75],"There":[76],"few":[78],"dedicated":[79,170],"datasets":[80],"training,":[83],"so":[84],"progress":[86],"of":[87,138,161,185,210],"study":[90],"slow":[92],"and":[93,113,125,152,212],"performance":[95],"poor.":[97],"Therefore,":[98],"we":[99,114,164,192],"presented":[100],"data":[101,132],"augmentation":[102,133],"method":[103],"based":[104],"on":[105],"TIMIT":[106],"dataset":[107],"suit":[109],"system,":[112,201],"also":[115],"proposed":[116,131,187,199],"several":[117],"methods":[118],"represent":[120],"systems":[124],"their":[126],"preliminary":[127,176],"results.":[128],"In":[129,189],"method,":[134],"boundary":[136],"information":[137,196],"transformed":[141],"probability":[143],"offset":[147],"given":[150],"frame":[151,213],"collected":[153],"segment.":[156],"To":[157],"boundaries":[160],"speakers,":[163],"concatenate":[165],"two":[166],"random":[167],"speech":[168,172],"sentences":[169],"recognition":[173],"system.":[174],"experimental":[177],"results,":[178],"specifically":[179],"recall":[180],"percentage,":[181],"shows":[182],"possibility":[184],"approaches.":[188],"future,":[191],"will":[193],"add":[194],"linguistic":[195],"classification":[200],"improve":[203],"use":[207],"hybrid":[208],"d-vector":[211],"vectors,":[214],"convolutional":[216],"networks.":[217]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}