{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GH4MLVE6YZJ6S647QCTPMFA247","short_pith_number":"pith:GH4MLVE6","schema_version":"1.0","canonical_sha256":"31f8c5d49ec653e97b9f80a6f6141ae7db3d87e2037236cc413fd65aff462f20","source":{"kind":"arxiv","id":"2405.19796","version":1},"attestation_state":"computed","paper":{"title":"Explainable Attribute-Based Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajitha Rajan, Chau Luu, Peter Bell, Xiaoliang Wu","submitted_at":"2024-05-30T08:04:28Z","abstract_excerpt":"This paper proposes a fully explainable approach to speaker verification (SV), a task that fundamentally relies on individual speaker characteristics. The opaque use of speaker attributes in current SV systems raises concerns of trust. Addressing this, we propose an attribute-based explainable SV system that identifies speakers by comparing personal attributes such as gender, nationality, and age extracted automatically from voice recordings. We believe this approach better aligns with human reasoning, making it more understandable than traditional methods. Evaluated on the Voxceleb1 test set,"},"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":"2405.19796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-05-30T08:04:28Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"59dc541ccc70dba28ab3557c362a6634d2d4463fa0fc5d5a4f8e1c8d5b53a57d","abstract_canon_sha256":"026c420fce0359a9aa87fa020fa0d804c4caa680e98a1dd845e4aa56cf1f1186"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:12.677094Z","signature_b64":"8/t12URT6yCNTXEiMwXCBgLCXru2bj0OSiTcPBTOfuQjAH8V2qWDJUetwwj0TrymnHPguyEZWfU3orrodDTHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31f8c5d49ec653e97b9f80a6f6141ae7db3d87e2037236cc413fd65aff462f20","last_reissued_at":"2026-07-05T08:25:12.676585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:12.676585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Attribute-Based Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ajitha Rajan, Chau Luu, Peter Bell, Xiaoliang Wu","submitted_at":"2024-05-30T08:04:28Z","abstract_excerpt":"This paper proposes a fully explainable approach to speaker verification (SV), a task that fundamentally relies on individual speaker characteristics. The opaque use of speaker attributes in current SV systems raises concerns of trust. Addressing this, we propose an attribute-based explainable SV system that identifies speakers by comparing personal attributes such as gender, nationality, and age extracted automatically from voice recordings. We believe this approach better aligns with human reasoning, making it more understandable than traditional methods. Evaluated on the Voxceleb1 test set,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19796","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/2405.19796/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":"2405.19796","created_at":"2026-07-05T08:25:12.676648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19796v1","created_at":"2026-07-05T08:25:12.676648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19796","created_at":"2026-07-05T08:25:12.676648+00:00"},{"alias_kind":"pith_short_12","alias_value":"GH4MLVE6YZJ6","created_at":"2026-07-05T08:25:12.676648+00:00"},{"alias_kind":"pith_short_16","alias_value":"GH4MLVE6YZJ6S647","created_at":"2026-07-05T08:25:12.676648+00:00"},{"alias_kind":"pith_short_8","alias_value":"GH4MLVE6","created_at":"2026-07-05T08:25:12.676648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08586","citing_title":"Why Do You Say It Like That? A Phoneme-Level Framework for Explainable Speech Deepfake Detection","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21305","citing_title":"LISE : Listenable Interpretable Speaker Embeddings","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21306","citing_title":"Towards Dys-XAI: Influence-Based Explanations for Dysarthria Severity Assessment","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15044","citing_title":"SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01590","citing_title":"PhiNet: Speaker Verification with Phonetic Interpretability","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247","json":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247.json","graph_json":"https://pith.science/api/pith-number/GH4MLVE6YZJ6S647QCTPMFA247/graph.json","events_json":"https://pith.science/api/pith-number/GH4MLVE6YZJ6S647QCTPMFA247/events.json","paper":"https://pith.science/paper/GH4MLVE6"},"agent_actions":{"view_html":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247","download_json":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247.json","view_paper":"https://pith.science/paper/GH4MLVE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19796&json=true","fetch_graph":"https://pith.science/api/pith-number/GH4MLVE6YZJ6S647QCTPMFA247/graph.json","fetch_events":"https://pith.science/api/pith-number/GH4MLVE6YZJ6S647QCTPMFA247/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247/action/storage_attestation","attest_author":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247/action/author_attestation","sign_citation":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247/action/citation_signature","submit_replication":"https://pith.science/pith/GH4MLVE6YZJ6S647QCTPMFA247/action/replication_record"}},"created_at":"2026-07-05T08:25:12.676648+00:00","updated_at":"2026-07-05T08:25:12.676648+00:00"}