{"id":"https://openalex.org/W3012250009","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023136","title":"Speaker Clustering with Penalty Distance for Speaker Verification with Multi-Speaker Speech","display_name":"Speaker Clustering with Penalty Distance for Speaker Verification with Multi-Speaker Speech","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012250009","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023136","mag":"3012250009"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406845","display_name":"Jichen Yang","orcid":"https://orcid.org/0000-0003-2655-8304"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jichen Yang","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029637694"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20755034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"24","issue":null,"first_page":"1630","last_page":"1635"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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":0.994700014591217,"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":0.7808564305305481},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7634145021438599},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7154736518859863},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7096402645111084},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6871869564056396},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6641981601715088},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6628298759460449},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5551742911338806},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5422959327697754},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.44285932183265686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38067305088043213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808564305305481},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7634145021438599},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7154736518859863},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7096402645111084},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6871869564056396},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6641981601715088},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6628298759460449},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5551742911338806},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5422959327697754},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.44285932183265686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38067305088043213},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W36432376","https://openalex.org/W1482605500","https://openalex.org/W1586405805","https://openalex.org/W1607302042","https://openalex.org/W1658556320","https://openalex.org/W1936725236","https://openalex.org/W2038101708","https://openalex.org/W2063511145","https://openalex.org/W2081074144","https://openalex.org/W2138730338","https://openalex.org/W2145540416","https://openalex.org/W2150769028","https://openalex.org/W2154278880","https://openalex.org/W2159591770","https://openalex.org/W2170088868","https://openalex.org/W2219249508","https://openalex.org/W2292479959","https://openalex.org/W2407688633","https://openalex.org/W2433551143","https://openalex.org/W2509346200","https://openalex.org/W2513379592","https://openalex.org/W2516631658","https://openalex.org/W2516764878","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2696990509","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2748643181","https://openalex.org/W2765399676","https://openalex.org/W2806563680","https://openalex.org/W2807629722","https://openalex.org/W2808631503","https://openalex.org/W2889381673","https://openalex.org/W2889418727","https://openalex.org/W2889496963","https://openalex.org/W2890964092","https://openalex.org/W2941320063","https://openalex.org/W2963422555","https://openalex.org/W2963978172","https://openalex.org/W2972712416","https://openalex.org/W4234330420","https://openalex.org/W6601517211","https://openalex.org/W6628911050","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W468945283","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"Speaker":[0,11],"verification":[1],"in":[2,30,39,65,108,118,133,148],"a":[3,21,31,57,61,85,109,150],"multi-speaker":[4,32,110,130],"environment":[5],"is":[6,34,102],"an":[7],"emerging":[8],"research":[9],"topic.":[10],"clustering,":[12],"that":[13,101,128],"separates":[14],"multiple":[15],"speakers,":[16],"can":[17],"be":[18],"effective":[19],"if":[20],"predetermined":[22],"threshold":[23],"or":[24],"the":[25,37,44,49,66,93,119,139,142],"number":[26,87],"of":[27,48,68,88,141],"speakers":[28,117],"present":[29],"utterance":[33],"given.":[35],"However,":[36],"problem":[38,58],"practice":[40],"does":[41],"not":[42],"provide":[43],"leverage":[45],"for":[46,84,104],"either":[47],"factors.":[50],"This":[51],"work":[52],"proposes":[53],"to":[54,80],"handle":[55],"such":[56,149],"by":[59],"introducing":[60],"penalty":[62,94,144],"distance":[63,95,145],"factor":[64],"pipeline":[67],"traditional":[69,77],"clustering":[70,78],"techniques.":[71],"The":[72,112,136],"proposed":[73,143],"framework":[74],"first":[75],"uses":[76],"techniques":[79],"form":[81],"speaker":[82],"clusters":[83,107],"given":[86],"speakers.":[89],"We":[90],"then":[91],"compute":[92],"based":[96,146],"on":[97,116],"Bayesian":[98],"information":[99],"criterion":[100],"used":[103],"merging":[105],"alike":[106],"utterance.":[111],"studies":[113],"are":[114],"conducted":[115],"wild":[120],"(SITW)":[121],"and":[122],"recent":[123],"NIST":[124],"SRE":[125],"2018":[126],"databases":[127],"contain":[129],"conversational":[131],"speech":[132],"noisy":[134],"environments.":[135],"results":[137],"show":[138],"effectiveness":[140],"refinement":[147],"scenario.":[151]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}