{"id":"https://openalex.org/W2963386851","doi":"https://doi.org/10.1109/icassp.2019.8683393","title":"Centroid-based Deep Metric Learning for Speaker Recognition","display_name":"Centroid-based Deep Metric Learning for Speaker Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963386851","doi":"https://doi.org/10.1109/icassp.2019.8683393","mag":"2963386851"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683393","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":"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/A5063578134","display_name":"Jixuan Wang","orcid":"https://orcid.org/0000-0003-1986-6747"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jixuan Wang","raw_affiliation_strings":["University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047870940","display_name":"Kuan-Chieh Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kuan-Chieh Wang","raw_affiliation_strings":["University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021018507","display_name":"Marc T. Law","orcid":"https://orcid.org/0000-0001-7767-2313"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marc T. Law","raw_affiliation_strings":["University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056256317","display_name":"Frank Rudzicz","orcid":"https://orcid.org/0000-0002-1139-3423"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Frank Rudzicz","raw_affiliation_strings":["University of Toronto, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012113499","display_name":"Michael Brudno","orcid":"https://orcid.org/0000-0001-7947-2243"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I2801317318","display_name":"Hospital for Sick Children","ror":"https://ror.org/057q4rt57","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2801317318"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Brudno","raw_affiliation_strings":["University of Toronto, Canada","Hospital for Sick Children, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Hospital for Sick Children, Canada","institution_ids":["https://openalex.org/I2801317318"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3652","last_page":"3656"},"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":0.9990000128746033,"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":0.9965999722480774,"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/embedding","display_name":"Embedding","score":0.7623959183692932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458006739616394},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.7011436223983765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6391670107841492},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6193723678588867},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6114442944526672},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5995755791664124},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5859792232513428},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5708571076393127},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5537612438201904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5110551118850708},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4810176491737366},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43972572684288025},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41527998447418213},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.32776641845703125}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7623959183692932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458006739616394},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.7011436223983765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6391670107841492},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6193723678588867},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6114442944526672},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5995755791664124},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5859792232513428},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5708571076393127},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5537612438201904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5110551118850708},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4810176491737366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43972572684288025},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41527998447418213},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32776641845703125},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683393","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2096733369","https://openalex.org/W2096765209","https://openalex.org/W2115733720","https://openalex.org/W2118393783","https://openalex.org/W2127589108","https://openalex.org/W2150769028","https://openalex.org/W2157364932","https://openalex.org/W2194321275","https://openalex.org/W2295300449","https://openalex.org/W2402704384","https://openalex.org/W2469455946","https://openalex.org/W2527729766","https://openalex.org/W2601450892","https://openalex.org/W2612434969","https://openalex.org/W2613997951","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2916128154","https://openalex.org/W2962788625","https://openalex.org/W2963702081","https://openalex.org/W2964121744","https://openalex.org/W3099206234","https://openalex.org/W6631190155","https://openalex.org/W6674201379","https://openalex.org/W6677884823","https://openalex.org/W6696886941","https://openalex.org/W6713082170","https://openalex.org/W6727697161","https://openalex.org/W6735236233","https://openalex.org/W6737575990","https://openalex.org/W6756040250","https://openalex.org/W6759652014"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"Speaker":[0],"embedding":[1,69,87],"models":[2,95],"that":[3],"utilize":[4],"neural":[5],"networks":[6],"to":[7,10,50],"map":[8],"utterances":[9],"a":[11,32,56,67,76],"space":[12],"where":[13,55],"distances":[14],"reflect":[15],"similarity":[16],"between":[17,36],"speakers":[18,38],"have":[19],"driven":[20],"recent":[21],"progress":[22],"in":[23,39,96],"the":[24,40,51,80,90],"speaker":[25,68,98],"recognition":[26],"task.":[27,84],"However,":[28],"there":[29],"is":[30,59],"still":[31],"significant":[33],"performance":[34],"gap":[35],"recognizing":[37],"training":[41],"set":[42],"and":[43,100,106],"unseen":[44,62,107],"speakers.":[45,108],"The":[46,85],"latter":[47],"case":[48],"corresponds":[49],"few-shot":[52,81],"learning":[53],"task,":[54],"trained":[57],"model":[58,70,88],"evaluated":[60],"on":[61],"classes.":[63],"Here,":[64],"we":[65],"optimize":[66],"with":[71],"prototypical":[72],"network":[73],"loss":[74,93],"(PNL),":[75],"state-of-the-art":[77,91],"approach":[78],"for":[79,103],"image":[82],"classification":[83],"resulting":[86],"outperforms":[89],"triplet":[92],"based":[94],"both":[97,104],"verification":[99],"identification":[101],"tasks,":[102],"seen":[105]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":23},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}