{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GXKJVG24AUUIWYJIJHCRSSFD42","short_pith_number":"pith:GXKJVG24","schema_version":"1.0","canonical_sha256":"35d49a9b5c05288b612849c51948a3e682a0157fbf1d0538b1cf52b08f614acd","source":{"kind":"arxiv","id":"2506.19446","version":1},"attestation_state":"computed","paper":{"title":"Vo-Ve: An Explainable Voice-Vector for Speaker Identity Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jaejun Lee, Kyogu Lee","submitted_at":"2025-06-24T09:20:25Z","abstract_excerpt":"In this paper, we propose Vo-Ve, a novel voice-vector embedding that captures speaker identity. Unlike conventional speaker embeddings, Vo-Ve is explainable, as it contains the probabilities of explicit voice attribute classes. Through extensive analysis, we demonstrate that Vo-Ve not only evaluates speaker similarity competitively with conventional techniques but also provides an interpretable explanation in terms of voice attributes. We strongly believe that Vo-Ve can enhance evaluation schemes across various speech tasks due to its high-level explainability."},"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":"2506.19446","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-24T09:20:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0fa784ec3927adcc01ce00c271dbcee4d85b9f0eb7a60cb65ec1e7c4ec5fb68a","abstract_canon_sha256":"6fa2bff614c271e1a6a4b8b0870a11136f15afaa4799462e325e3e3fa6dddf2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:33.835048Z","signature_b64":"H7W9kC/cEWwhohZXMe2AszLf2Exn4oo2g2Si4P2H5KdoM4ZOJrDPwTan2VY6HcfbABa7BnYtELVQh0n6ef63Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d49a9b5c05288b612849c51948a3e682a0157fbf1d0538b1cf52b08f614acd","last_reissued_at":"2026-07-05T11:26:33.834491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:33.834491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vo-Ve: An Explainable Voice-Vector for Speaker Identity Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jaejun Lee, Kyogu Lee","submitted_at":"2025-06-24T09:20:25Z","abstract_excerpt":"In this paper, we propose Vo-Ve, a novel voice-vector embedding that captures speaker identity. Unlike conventional speaker embeddings, Vo-Ve is explainable, as it contains the probabilities of explicit voice attribute classes. Through extensive analysis, we demonstrate that Vo-Ve not only evaluates speaker similarity competitively with conventional techniques but also provides an interpretable explanation in terms of voice attributes. We strongly believe that Vo-Ve can enhance evaluation schemes across various speech tasks due to its high-level explainability."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19446","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/2506.19446/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":"2506.19446","created_at":"2026-07-05T11:26:33.834574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19446v1","created_at":"2026-07-05T11:26:33.834574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19446","created_at":"2026-07-05T11:26:33.834574+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXKJVG24AUUI","created_at":"2026-07-05T11:26:33.834574+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXKJVG24AUUIWYJI","created_at":"2026-07-05T11:26:33.834574+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXKJVG24","created_at":"2026-07-05T11:26:33.834574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21305","citing_title":"LISE : Listenable Interpretable Speaker Embeddings","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42","json":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42.json","graph_json":"https://pith.science/api/pith-number/GXKJVG24AUUIWYJIJHCRSSFD42/graph.json","events_json":"https://pith.science/api/pith-number/GXKJVG24AUUIWYJIJHCRSSFD42/events.json","paper":"https://pith.science/paper/GXKJVG24"},"agent_actions":{"view_html":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42","download_json":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42.json","view_paper":"https://pith.science/paper/GXKJVG24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19446&json=true","fetch_graph":"https://pith.science/api/pith-number/GXKJVG24AUUIWYJIJHCRSSFD42/graph.json","fetch_events":"https://pith.science/api/pith-number/GXKJVG24AUUIWYJIJHCRSSFD42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42/action/storage_attestation","attest_author":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42/action/author_attestation","sign_citation":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42/action/citation_signature","submit_replication":"https://pith.science/pith/GXKJVG24AUUIWYJIJHCRSSFD42/action/replication_record"}},"created_at":"2026-07-05T11:26:33.834574+00:00","updated_at":"2026-07-05T11:26:33.834574+00:00"}