{"id":"https://openalex.org/W2972956697","doi":"https://doi.org/10.21437/interspeech.2019-2486","title":"VAE-Based Regularization for Deep Speaker Embedding","display_name":"VAE-Based Regularization for Deep Speaker Embedding","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972956697","doi":"https://doi.org/10.21437/interspeech.2019-2486","mag":"2972956697"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2486","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5100354801","display_name":"Yang Zhang","orcid":"https://orcid.org/0000-0003-3383-7889"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yang Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100354801"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2403,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90985266,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4020","last_page":"4024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9948999881744385,"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/regularization","display_name":"Regularization (linguistics)","score":0.8314254283905029},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8267785906791687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6986833214759827},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6552502512931824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5623060464859009},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.553591787815094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49726131558418274},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4929828345775604},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.47213083505630493},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4666818082332611},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4455469846725464},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38382333517074585},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35868358612060547}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.8314254283905029},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8267785906791687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6986833214759827},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6552502512931824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623060464859009},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.553591787815094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49726131558418274},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4929828345775604},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.47213083505630493},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4666818082332611},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4455469846725464},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38382333517074585},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35868358612060547},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-2486","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Deep":[0],"speaker":[1,8],"embedding":[2],"has":[3],"achieved":[4],"state-of-the-art":[5],"performance":[6,23],"in":[7],"recognition.":[9],"A":[10],"potential":[11],"problem":[12],"of":[13],"these":[14],"embedded":[15],"vectors":[16],"(called":[17],"`x-vectors')":[18],"are":[19,56],"not":[20],"Gaussian,":[21,58],"causing":[22],"degradation":[24],"with":[25],"the":[26],"famous":[27],"PLDA":[28,63],"back-end":[29],"scoring.":[30,64],"In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"a":[36,49],"regularization":[37],"approach":[38],"based":[39],"on":[40],"Variational":[41],"Auto-Encoder":[42],"(VAE).":[43],"This":[44],"model":[45],"transforms":[46],"x-vectors":[47],"to":[48],"latent":[50,54],"space":[51],"where":[52],"mapped":[53],"codes":[55],"more":[57,60],"hence":[59],"suitable":[61],"for":[62]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}