{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EPUDTXOLTARB4PPAPS6ZPEWWOL","short_pith_number":"pith:EPUDTXOL","schema_version":"1.0","canonical_sha256":"23e839ddcb98221e3de07cbd9792d672c26ded2fe0009d984d823a5acb338e2b","source":{"kind":"arxiv","id":"2407.18505","version":1},"attestation_state":"computed","paper":{"title":"VoxSim: A perceptual voice similarity dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Doyeop Kwak, Ji-Hoon Kim, Joon Son Chung, Junseok Ahn, Seongkyu Mun, Yeunju Choi, Youkyum Kim","submitted_at":"2024-07-26T04:27:13Z","abstract_excerpt":"This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice similarity relatively unexplored due to a lack of extensive training data. To address this, we generate about 41k utterance pairs from the VoxCeleb dataset, a widely utilised speech dataset for speaker recognition, and collect nearly 70k speaker similarity scores through a listening test. VoxSim offers a valuable resource for the development and ben"},"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":"2407.18505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-26T04:27:13Z","cross_cats_sorted":[],"title_canon_sha256":"12637e4f05b73fe6fe97ccb735b632c46f28c8dd58d671fdb5d623c0de387567","abstract_canon_sha256":"4eb1ce6fba0cf42724f8043911bc344b80ba410c572060078540686014e26f7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:50.665463Z","signature_b64":"5hfvvckzcmRGWTHuJKpl1l/TOzs5zhyGQrI/ZVgIvp7d+2kzCB1XkWW77MUAoIGGO9Liel1+TQ31puJMa05ICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e839ddcb98221e3de07cbd9792d672c26ded2fe0009d984d823a5acb338e2b","last_reissued_at":"2026-07-05T08:48:50.664949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:50.664949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxSim: A perceptual voice similarity dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Doyeop Kwak, Ji-Hoon Kim, Joon Son Chung, Junseok Ahn, Seongkyu Mun, Yeunju Choi, Youkyum Kim","submitted_at":"2024-07-26T04:27:13Z","abstract_excerpt":"This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice similarity relatively unexplored due to a lack of extensive training data. To address this, we generate about 41k utterance pairs from the VoxCeleb dataset, a widely utilised speech dataset for speaker recognition, and collect nearly 70k speaker similarity scores through a listening test. VoxSim offers a valuable resource for the development and ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18505","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/2407.18505/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":"2407.18505","created_at":"2026-07-05T08:48:50.665005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18505v1","created_at":"2026-07-05T08:48:50.665005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18505","created_at":"2026-07-05T08:48:50.665005+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPUDTXOLTARB","created_at":"2026-07-05T08:48:50.665005+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPUDTXOLTARB4PPA","created_at":"2026-07-05T08:48:50.665005+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPUDTXOL","created_at":"2026-07-05T08:48:50.665005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00733","citing_title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL","json":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL.json","graph_json":"https://pith.science/api/pith-number/EPUDTXOLTARB4PPAPS6ZPEWWOL/graph.json","events_json":"https://pith.science/api/pith-number/EPUDTXOLTARB4PPAPS6ZPEWWOL/events.json","paper":"https://pith.science/paper/EPUDTXOL"},"agent_actions":{"view_html":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL","download_json":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL.json","view_paper":"https://pith.science/paper/EPUDTXOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18505&json=true","fetch_graph":"https://pith.science/api/pith-number/EPUDTXOLTARB4PPAPS6ZPEWWOL/graph.json","fetch_events":"https://pith.science/api/pith-number/EPUDTXOLTARB4PPAPS6ZPEWWOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL/action/storage_attestation","attest_author":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL/action/author_attestation","sign_citation":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL/action/citation_signature","submit_replication":"https://pith.science/pith/EPUDTXOLTARB4PPAPS6ZPEWWOL/action/replication_record"}},"created_at":"2026-07-05T08:48:50.665005+00:00","updated_at":"2026-07-05T08:48:50.665005+00:00"}