{"id":"https://openalex.org/W2939061993","doi":"https://doi.org/10.1109/icassp.2019.8683148","title":"The Leap Speaker Recognition System for NIST SRE 2018 Challenge","display_name":"The Leap Speaker Recognition System for NIST SRE 2018 Challenge","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939061993","doi":"https://doi.org/10.1109/icassp.2019.8683148","mag":"2939061993"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/78385/1/MPRA_paper_78385.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113091984","display_name":"Shreyas Ramoji","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreyas Ramoji","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011775237","display_name":"Anand Mohan","orcid":"https://orcid.org/0000-0001-5177-8291"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anand Mohan","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029788771","display_name":"Bhargavram Mysore","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhargavram Mysore","raw_affiliation_strings":["North Carolina State University, North Carolina, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020724703","display_name":"Anmol Bhatia","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anmol Bhatia","raw_affiliation_strings":["Birla Institute of Technology and Sciences (BITS), Pilani, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Sciences (BITS), Pilani, India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101528020","display_name":"Prachi Singh","orcid":"https://orcid.org/0000-0003-0760-8572"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prachi Singh","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112222277","display_name":"Harsha Vardhan","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harsha Vardhan","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536077","display_name":"Sriram Ganapathy","orcid":"https://orcid.org/0000-0002-5779-9066"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Ganapathy","raw_affiliation_strings":["Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Learning and Extraction of Acoustic Patterns (LEAP) Lab, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8676,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80437995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5771","last_page":"5775"},"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":0.9968000054359436,"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":0.9854000210762024,"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/nist","display_name":"NIST","score":0.9611850380897522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914265394210815},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6905488967895508},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6866130232810974},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5410692691802979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344654321670532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5177449584007263},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4837222397327423},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47786206007003784},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4711315333843231},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42247647047042847}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9611850380897522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914265394210815},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6905488967895508},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6866130232810974},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5410692691802979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344654321670532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5177449584007263},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4837222397327423},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47786206007003784},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4711315333843231},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42247647047042847},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai::78385","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/78385/1/MPRA_paper_78385.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai::78385","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/78385/1/MPRA_paper_78385.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2939061993.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W199121787","https://openalex.org/W1524333225","https://openalex.org/W1836183712","https://openalex.org/W1909308924","https://openalex.org/W1916834241","https://openalex.org/W1965819578","https://openalex.org/W1971758513","https://openalex.org/W1990942610","https://openalex.org/W2039057510","https://openalex.org/W2041823554","https://openalex.org/W2107638917","https://openalex.org/W2124112941","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2281877999","https://openalex.org/W2360384684","https://openalex.org/W2395750323","https://openalex.org/W2405584646","https://openalex.org/W2406312423","https://openalex.org/W2587150483","https://openalex.org/W2890830077","https://openalex.org/W2890964092","https://openalex.org/W2962853205","https://openalex.org/W2963068250","https://openalex.org/W6608088770","https://openalex.org/W6631362777","https://openalex.org/W6638844259","https://openalex.org/W6639916541","https://openalex.org/W6640010188","https://openalex.org/W6713727690","https://openalex.org/W6713741301"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"The":[0,95,117],"NIST":[1,30,157,180],"Speaker":[2],"Recognition":[3],"Evaluation":[4],"(SRE)":[5],"2018":[6,143],"challenge":[7],"comprises":[8],"an":[9],"open":[10],"evaluation":[11,194],"of":[12,46,149,161,170,186],"the":[13,22,29,35,39,44,76,79,104,128,141,150,156,162,171,179,191],"text":[14],"independent":[15],"speaker":[16,24,36,59,72,100,111],"verification":[17,25,37,73,112],"task.":[18,61,74],"This":[19],"paper":[20],"summarizes":[21],"LEAP":[23],"systems":[26,151],"submitted":[27],"to":[28],"SRE":[31,142],"2018.":[32],"For":[33],"all":[34],"approaches,":[38,173],"front-end":[40],"feature":[41],"extraction":[42],"involved":[43],"use":[45],"neural":[47,53],"embeddings":[48],"from":[49],"a":[50,58,99,121,135,167],"time":[51],"delay":[52],"network":[54],"(TDNN)":[55],"trained":[56],"on":[57,103,115,140],"discrimination":[60],"These":[62],"features,":[63],"called":[64],"x-vectors,":[65],"are":[66,86,131],"used":[67,87],"in":[68,159],"multiple":[69,108],"ways":[70],"for":[71,126,190],"In":[75],"first":[77],"approach,":[78],"x-vectors":[80,129],"with":[81,88],"pre-processing":[82,127],"and":[83,188,193],"dimensionality":[84],"reduction,":[85],"probabilistic":[89],"linear":[90],"discriminant":[91],"analysis":[92],"(PLDA)":[93],"scoring.":[94],"second":[96],"approach":[97],"applies":[98],"diarization":[101],"scheme":[102],"test":[105],"segments":[106],"containing":[107],"talkers":[109],"before":[110],"scoring":[113],"based":[114],"PLDA.":[116],"third":[118],"system":[119,168],"uses":[120],"local":[122],"pairwise":[123],"LDA":[124],"model":[125],"which":[130],"then":[132],"scored":[133],"using":[134],"Gaussian":[136],"back-end.":[137],"With":[138],"experiments":[139],"database,":[144],"we":[145,174],"show":[146],"that":[147],"most":[148],"achieved":[152],"noticeable":[153],"improvements":[154,177,185],"over":[155,178],"baseline":[158,182],"terms":[160],"primary":[163],"cost":[164],"metric.":[165],"Using":[166],"fusion":[169],"various":[172],"obtain":[175],"significant":[176],"official":[181],"(average":[183],"relative":[184],"19.7%":[187],"20.1%":[189],"development":[192],"set":[195],"respectively).":[196]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}