{"id":"https://openalex.org/W4385823373","doi":"https://doi.org/10.21437/interspeech.2023-453","title":"Improving Speaker Verification with Self-Pretrained Transformer Models","display_name":"Improving Speaker Verification with Self-Pretrained Transformer Models","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823373","doi":"https://doi.org/10.21437/interspeech.2023-453"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-453","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5111291634","display_name":"Junyi Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyi Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064238041","display_name":"Old\u0159ich Plchot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Old\u0159ich Plchot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055201620","display_name":"Ladislav Mo\u0161ner","orcid":"https://orcid.org/0000-0001-8175-2244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ladislav Mosner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan \"Honza\" \u010cernock\u00fd","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":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5361","last_page":"5365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9760000109672546,"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":0.7606112360954285},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6677850484848022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5107102394104004},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.47565028071403503},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3212643265724182},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24560096859931946},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12304171919822693},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12212991714477539},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07521712779998779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7606112360954285},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6677850484848022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5107102394104004},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.47565028071403503},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3212643265724182},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24560096859931946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12304171919822693},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12212991714477539},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07521712779998779}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-453","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2546089952","https://openalex.org/W2090976131","https://openalex.org/W2140022733","https://openalex.org/W1516392727"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
