{"id":"https://openalex.org/W4307536853","doi":"https://doi.org/10.48550/arxiv.2210.15385","title":"Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs","display_name":"Self-Supervised Training of Speaker Encoder with Multi-Modal Diverse Positive Pairs","publication_year":2022,"publication_date":"2022-10-27","ids":{"openalex":"https://openalex.org/W4307536853","doi":"https://doi.org/10.48550/arxiv.2210.15385"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.15385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.15385","pdf_url":"https://arxiv.org/pdf/2210.15385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.15385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Ruijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Kong Aik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Rohan Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hautam\u00e4ki, Ville","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haizhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9936000108718872,"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":0.982200026512146,"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":0.7564496994018555},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6741544008255005},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.621890127658844},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5938795804977417},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5538406372070312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5495747327804565},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5483832359313965},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5393123626708984},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5321226716041565},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45839014649391174},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4334661662578583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564496994018555},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6741544008255005},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.621890127658844},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5938795804977417},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5538406372070312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5495747327804565},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5483832359313965},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5393123626708984},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5321226716041565},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45839014649391174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4334661662578583},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.15385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.15385","pdf_url":"https://arxiv.org/pdf/2210.15385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.15385","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.15385","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.15385","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.15385","pdf_url":"https://arxiv.org/pdf/2210.15385","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.6800000071525574}],"awards":[{"id":"https://openalex.org/G3655129345","display_name":null,"funder_award_id":"EXC-2077","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W1556857061"],"abstract_inverted_index":{"We":[0,139,218],"study":[1,119],"a":[2,28,33,42,72,94,102,120,203],"novel":[3,108,194],"neural":[4,242],"architecture":[5,243],"and":[6,63,115,152,162,170,176,227,244],"its":[7],"training":[8,92],"strategies":[9,246],"of":[10,36,50,61,75,93,135,159,173,191],"speaker":[11,14,22,30,52,137,142,150,232],"encoder":[12,23,53,143],"for":[13,90,128],"recognition":[15],"without":[16,148],"using":[17],"any":[18,149],"identity":[19],"labels.":[20],"The":[21],"is":[24,41,67,234],"trained":[25],"to":[26],"extract":[27],"fixed-size":[29],"embedding":[31],"from":[32,77],"spoken":[34],"utterance":[35],"various":[37],"length.":[38],"Contrastive":[39],"learning":[40,45,105,181,200,216,223],"typical":[43],"self-supervised":[44,199,222],"technique.":[46],"However,":[47],"the":[48,51,58,78,91,133,136,141,145,165,179,187,197,207,214,231,240],"quality":[49],"depends":[54],"very":[55],"much":[56],"on":[57,144,186,225],"sampling":[59,109,245],"strategy":[60,182],"positive":[62,73,84,125],"negative":[64],"pairs.":[65],"It":[66],"common":[68],"that":[69,122,239],"we":[70,100,118],"sample":[71],"pair":[74],"segments":[76],"same":[79,208],"utterance.":[80],"Unfortunately,":[81],"such":[82],"poor-man's":[83],"pairs":[85,126],"(PPP)":[86],"lack":[87],"necessary":[88],"diversity":[89],"robust":[95,248],"encoder.":[96,138],"In":[97],"this":[98],"work,":[99],"propose":[101],"multi-modal":[103],"contrastive":[104,129],"technique":[106,224],"with":[107,183,213],"strategies.":[110],"By":[111],"cross-referencing":[112],"between":[113],"speech":[114],"face":[116],"data,":[117],"method":[121],"finds":[123],"diverse":[124],"(DPP)":[127],"learning,":[130],"thus":[131],"improving":[132],"robustness":[134],"train":[140],"VoxCeleb2":[146],"dataset":[147],"labels,":[151,185],"achieve":[153],"an":[154,171],"equal":[155],"error":[156],"rate":[157],"(EER)":[158],"2.89\\%,":[160],"3.17\\%":[161],"6.27\\%":[163],"under":[164,178],"proposed":[166,241],"progressive":[167],"clustering":[168],"strategy,":[169],"EER":[172],"1.44\\%,":[174],"1.77\\%":[175],"3.27\\%":[177],"two-stage":[180],"pseudo":[184],"three":[188],"test":[189],"sets":[190],"VoxCeleb1.":[192],"This":[193],"solution":[195],"outperforms":[196],"state-of-the-art":[198],"methods":[201],"by":[202],"large":[204],"margin,":[205],"at":[206],"time,":[209],"achieves":[210],"comparable":[211],"results":[212],"supervised":[215],"counterpart.":[217],"also":[219],"evaluate":[220],"our":[221],"LRS2":[226],"LRW":[228],"datasets,":[229],"where":[230],"information":[233],"unknown.":[235],"All":[236],"experiments":[237],"suggest":[238],"are":[247],"across":[249],"datasets.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}