{"id":"https://openalex.org/W4408345934","doi":"https://doi.org/10.1109/icassp49660.2025.10888116","title":"Energy-based Model Guided Self-Supervised Learning for Speaker Verification","display_name":"Energy-based Model Guided Self-Supervised Learning for Speaker Verification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345934","doi":"https://doi.org/10.1109/icassp49660.2025.10888116"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101370262","display_name":"Yaqian Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqian Hao","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018560999","display_name":"Chenguang Hu","orcid":"https://orcid.org/0000-0003-1880-5520"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenguang Hu","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055412406","display_name":"Chong Bian","orcid":"https://orcid.org/0000-0001-7436-8252"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Bian","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079750750","display_name":"Junlan Feng","orcid":"https://orcid.org/0000-0001-5292-2945"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068298033","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-6869-3013"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032367559","display_name":"Shilei Zhang","orcid":"https://orcid.org/0000-0001-8169-0098"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["China Mobile Research Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute,Beijing,China","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I180662265"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9872000217437744,"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":0.9872000217437744,"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":0.9016000032424927,"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":0.8023234605789185},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7199152708053589},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5333471298217773},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.47998663783073425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42229312658309937},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3675291836261749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8023234605789185},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7199152708053589},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5333471298217773},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.47998663783073425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42229312658309937},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3675291836261749},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":21,"referenced_works":["https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W3188049289","https://openalex.org/W3205635414","https://openalex.org/W3206189675","https://openalex.org/W4289792473","https://openalex.org/W4296068770","https://openalex.org/W4319862473","https://openalex.org/W4372340947","https://openalex.org/W4386075769","https://openalex.org/W4387557508","https://openalex.org/W4388579618","https://openalex.org/W4392811557","https://openalex.org/W4392910494","https://openalex.org/W4396733589","https://openalex.org/W6688816777","https://openalex.org/W6767220907","https://openalex.org/W6771731465","https://openalex.org/W6784323503","https://openalex.org/W6850203366"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,60],"(SSL)":[2],"has":[3],"significantly":[4],"advanced":[5],"speaker":[6,26,84,93],"verification,":[7],"especially":[8],"in":[9],"scenarios":[10],"with":[11,37,95],"limited":[12],"labeled":[13],"data.":[14],"This":[15,80],"paper":[16],"introduces":[17],"Energy-based":[18],"Confidence-Aware":[19],"Distillation":[20],"(EBCA-DINO),":[21],"an":[22],"SSL":[23],"enhancement":[24],"for":[25],"verification":[27,85,94],"that":[28,90],"integrates":[29],"Energy-Based":[30],"Models":[31],"(EBMs)":[32],"into":[33],"the":[34,59,66,72,105],"DINO":[35],"(Distillation":[36],"No":[38],"Labels)":[39],"framework.":[40],"EBMs":[41],"use":[42],"energy":[43],"scores":[44],"to":[45,62,69],"assess":[46],"data":[47,63],"complexity":[48],"and":[49,102,108],"uncertainty,":[50],"guiding":[51],"label-free":[52],"self-distillation.":[53],"The":[54],"adaptive":[55],"temperature":[56],"scaling":[57],"tailors":[58],"process":[61],"characteristics,":[64],"allowing":[65],"teacher":[67],"model":[68],"dynamically":[70],"adjust":[71],"student":[73],"model\u2019s":[74],"focus":[75],"based":[76],"on":[77,104],"sample":[78],"difficulty.":[79],"energy-aware":[81],"distillation":[82],"optimizes":[83],"performance.":[86],"Experimental":[87],"results":[88],"demonstrate":[89],"EBCA-DINO":[91],"improves":[92],"relative":[96],"performance":[97],"gains":[98],"of":[99],"4.3%,":[100],"4.9%,":[101],"8.7%":[103],"Vox1-O,":[106],"E,":[107],"H":[109],"test":[110],"trials,":[111],"respectively.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}