{"id":"https://openalex.org/W4416249819","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227873","title":"Sample-to-Sample Learning and inverted bottleneck for Speaker Verification","display_name":"Sample-to-Sample Learning and inverted bottleneck for Speaker Verification","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416249819","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227873"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5101732742","display_name":"Yi\u2010Hao Chen","orcid":"https://orcid.org/0000-0002-9977-7180"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Chen","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045230762","display_name":"Jialong Wang","orcid":"https://orcid.org/0009-0008-7961-8511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialong Wang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067270756","display_name":"Yunqi Hao","orcid":"https://orcid.org/0000-0002-6838-1511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunqi Hao","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413867","display_name":"Minqiang Xu","orcid":"https://orcid.org/0000-0003-3625-1736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minqiang Xu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074900997","display_name":"Jianbo Zhan","orcid":"https://orcid.org/0000-0002-5885-1970"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianbo Zhan","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067399917","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-2218-005X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044739051","display_name":"Lei Fang","orcid":"https://orcid.org/0000-0002-1438-2500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Sian Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sian Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32109408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9460999965667725,"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":0.9460999965667725,"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":0.006200000178068876,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.00570000009611249,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.85589998960495},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8533999919891357},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6917999982833862},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3723999857902527},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.334199994802475}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.85589998960495},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8533999919891357},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6917999982833862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6697999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47920000553131104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.31470000743865967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2766999900341034},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27160000801086426},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":20,"referenced_works":["https://openalex.org/W2091432990","https://openalex.org/W2194775991","https://openalex.org/W2402146185","https://openalex.org/W2530876040","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962898354","https://openalex.org/W2963163009","https://openalex.org/W2969985801","https://openalex.org/W2970413753","https://openalex.org/W2972986505","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3176579584","https://openalex.org/W3205310163","https://openalex.org/W4312443924"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,9,54,57,76,84],"Sample-to-Sample":[4],"Learning":[5],"(S2SL)":[6],"technique":[7],"and":[8,18,34,44,75,83],"inverted":[10,58,77,85],"bottleneck":[11,59],"structure":[12],"for":[13],"speaker":[14,61],"verification.":[15,62],"Traditional":[16],"softmax":[17,20,73],"margin-based":[19,72],"losses":[21,74],"primarily":[22],"optimize":[23],"sample-to-prototype":[24,43],"similarity":[25],"while":[26],"overlooking":[27],"sample-to-sample":[28,45],"relationships.":[29],"To":[30],"address":[31],"this":[32],"limitation":[33],"minimize":[35],"intra-class":[36],"variance,":[37],"we":[38,52,87],"propose":[39],"S2SL,":[40],"which":[41],"integrates":[42],"similarities":[46],"through":[47],"a":[48],"linear":[49],"combination.":[50],"Additionally,":[51],"confirm":[53],"effectiveness":[55],"of":[56],"in":[60],"Our":[63],"experiments":[64],"demonstrate":[65],"that":[66],"S2SL":[67,82],"is":[68],"complementary":[69],"to":[70],"existing":[71],"bottleneck.":[78],"By":[79],"incorporating":[80],"both":[81],"bottleneck,":[86],"achieve":[88],"state-of-the-art":[89],"performance":[90],"across":[91],"multiple":[92],"benchmark":[93],"datasets.":[94]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-14T00:00:00"}