{"id":"https://openalex.org/W3162184950","doi":"https://doi.org/10.1109/icassp39728.2021.9413739","title":"Improving Reconstruction Loss Based Speaker Embedding in Unsupervised and Semi-Supervised Scenarios","display_name":"Improving Reconstruction Loss Based Speaker Embedding in Unsupervised and Semi-Supervised Scenarios","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162184950","doi":"https://doi.org/10.1109/icassp39728.2021.9413739","mag":"3162184950"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5059500729","display_name":"Jaejin Cho","orcid":"https://orcid.org/0000-0001-5672-6765"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaejin Cho","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Zelasko","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus Villalba","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,MD,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059500729"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0588789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6733","last_page":"6737"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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":0.9979000091552734,"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":0.7629448175430298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.694240927696228},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6722159385681152},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6407515406608582},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.633822500705719},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5953429937362671},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5524696707725525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5342117547988892},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5000402927398682},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48689737915992737},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.42537909746170044},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.416401207447052},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07255962491035461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629448175430298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.694240927696228},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6722159385681152},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6407515406608582},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.633822500705719},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5953429937362671},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5524696707725525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5342117547988892},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5000402927398682},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48689737915992737},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.42537909746170044},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.416401207447052},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07255962491035461},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2194775991","https://openalex.org/W2406312423","https://openalex.org/W2514741789","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2842511635","https://openalex.org/W2888867175","https://openalex.org/W2962898354","https://openalex.org/W2963371159","https://openalex.org/W2963432880","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972705840","https://openalex.org/W2972743990","https://openalex.org/W2979593053","https://openalex.org/W2981087920","https://openalex.org/W2981461916","https://openalex.org/W3010925296","https://openalex.org/W3016175755","https://openalex.org/W3036601975","https://openalex.org/W3097448764","https://openalex.org/W3099782249","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4288091954","https://openalex.org/W4297808394","https://openalex.org/W6631362777","https://openalex.org/W6713727690","https://openalex.org/W6748257384","https://openalex.org/W6752888775","https://openalex.org/W6769178842","https://openalex.org/W6780218876"],"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":{"Text-to-speech":[0],"(TTS)":[1],"models":[2],"trained":[3],"to":[4,123,180,191],"minimize":[5],"the":[6,46,63,88,96,103,108,125,136,139,145,170],"spectrogram":[7,64,97],"reconstruction":[8,163],"loss":[9,164],"can":[10,32],"learn":[11],"speaker":[12,16,21,29,50,58,109,141,148,151,166,185],"embeddings":[13,59],"without":[14,133],"explicit":[15],"identity":[17],"supervision,":[18],"unlike":[19],"x-vector":[20],"identification":[22],"(SID)":[23],"systems.":[24],"Leveraging":[25],"this":[26,54],"way":[27],"of":[28,45,98],"embedding":[30,110,142,167],"learning":[31],"be":[33],"useful":[34],"in":[35,53,120,150,156,177,184],"unsupervised":[36,68,137,147],"or":[37,42],"semi-supervised":[38,70,171],"scenarios":[39],"where":[40,95],"non,":[41],"only":[43],"some,":[44],"training":[47,62,178],"data":[48,76,176],"have":[49],"labels.":[51],"Thus,":[52],"paper,":[55],"we":[56],"evaluate":[57],"learned":[60],"by":[61,117,153,197],"prediction":[65],"network":[66],"under":[67],"and":[69,93,107,131,165],"scenarios.":[71],"We":[72,158],"experimented":[73],"with":[74],"different":[75,85],"sampling":[77,83],"strategies.":[78],"The":[79],"best":[80,140],"one":[81],"was":[82],"two":[84],"segments":[86],"from":[87,112],"same":[89,126],"utterance,":[90],"namely":[91],"A":[92,130],"B,":[94],"B":[99,104,132],"is":[100],"predicted":[101],"given":[102],"phone":[105],"sequence":[106],"extracted":[111],"A.":[113],"This":[114],"method":[115],"improved":[116,195],"3.4%":[118],"relative":[119,155],"EER,":[121],"compared":[122],"using":[124],"utterance":[127],"for":[128],"both":[129],"segmenting.":[134],"In":[135,169],"scenario,":[138,172],"outperformed":[143],"i-vectors,":[144],"state-of-the-art":[146],"embedding,":[149],"verification":[152],"12.9%":[154],"EER.":[157],"observed":[159],"high":[160],"correlation":[161],"between":[162],"quality.":[168],"having":[173],"more":[174],"unlabeled":[175,189],"led":[179],"a":[181],"better":[182],"performance":[183],"verification.":[186],"Adding":[187],"5314":[188],"speakers":[190,194],"800":[192],"labeled":[193],"EER":[196],"10.8":[198],"%":[199],"relative.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}