{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LCUR76RTHXJQIPSF2FO5MGJUMF","short_pith_number":"pith:LCUR76RT","schema_version":"1.0","canonical_sha256":"58a91ffa333dd3043e45d15dd619346140d5db1d4c41a7fb6bce4e02111f47c5","source":{"kind":"arxiv","id":"2506.07536","version":1},"attestation_state":"computed","paper":{"title":"Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hynek Hermansky, Jin Li, Johan Rohdin, Kong Aik Lee, Man-Wai Mak","submitted_at":"2025-06-09T08:18:12Z","abstract_excerpt":"The performance of automatic speaker verification (ASV) and anti-spoofing drops seriously under real-world domain mismatch conditions. The relaxed instance frequency-wise normalization (RFN), which normalizes the frequency components based on the feature statistics along the time and channel axes, is a promising approach to reducing the domain dependence in the feature maps of a speaker embedding network. We advocate that the different frequencies should receive different weights and that the weights' uncertainty due to domain shift should be accounted for. To these ends, we propose leveraging"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.07536","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T08:18:12Z","cross_cats_sorted":[],"title_canon_sha256":"d365e40f946ffaf30c24e45fb803aa38e45f34faf6c164bf6d1b3f692f8cc0f0","abstract_canon_sha256":"13037c5725ae1ccdd3886f25c08b90993752bdd637978da8ae5d04cf4acef0be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:28.979269Z","signature_b64":"X7Ht6aksUph+NAOtVDXaVtYA1eiZhkGjckhU6LHI9qdyywM9Qh5r8kWM24hi2x1lOnU9ATwrvixDwE8x86QcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58a91ffa333dd3043e45d15dd619346140d5db1d4c41a7fb6bce4e02111f47c5","last_reissued_at":"2026-07-05T11:18:28.978775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:28.978775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hynek Hermansky, Jin Li, Johan Rohdin, Kong Aik Lee, Man-Wai Mak","submitted_at":"2025-06-09T08:18:12Z","abstract_excerpt":"The performance of automatic speaker verification (ASV) and anti-spoofing drops seriously under real-world domain mismatch conditions. The relaxed instance frequency-wise normalization (RFN), which normalizes the frequency components based on the feature statistics along the time and channel axes, is a promising approach to reducing the domain dependence in the feature maps of a speaker embedding network. We advocate that the different frequencies should receive different weights and that the weights' uncertainty due to domain shift should be accounted for. To these ends, we propose leveraging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07536","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.07536/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.07536","created_at":"2026-07-05T11:18:28.978836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07536v1","created_at":"2026-07-05T11:18:28.978836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07536","created_at":"2026-07-05T11:18:28.978836+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCUR76RTHXJQ","created_at":"2026-07-05T11:18:28.978836+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCUR76RTHXJQIPSF","created_at":"2026-07-05T11:18:28.978836+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCUR76RT","created_at":"2026-07-05T11:18:28.978836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07536","citing_title":"Bayesian Learning for Domain-Invariant Speaker Verification and Anti-Spoofing","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF","json":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF.json","graph_json":"https://pith.science/api/pith-number/LCUR76RTHXJQIPSF2FO5MGJUMF/graph.json","events_json":"https://pith.science/api/pith-number/LCUR76RTHXJQIPSF2FO5MGJUMF/events.json","paper":"https://pith.science/paper/LCUR76RT"},"agent_actions":{"view_html":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF","download_json":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF.json","view_paper":"https://pith.science/paper/LCUR76RT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07536&json=true","fetch_graph":"https://pith.science/api/pith-number/LCUR76RTHXJQIPSF2FO5MGJUMF/graph.json","fetch_events":"https://pith.science/api/pith-number/LCUR76RTHXJQIPSF2FO5MGJUMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF/action/storage_attestation","attest_author":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF/action/author_attestation","sign_citation":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF/action/citation_signature","submit_replication":"https://pith.science/pith/LCUR76RTHXJQIPSF2FO5MGJUMF/action/replication_record"}},"created_at":"2026-07-05T11:18:28.978836+00:00","updated_at":"2026-07-05T11:18:28.978836+00:00"}