{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4JSJX2IO5SQ74SMNEYZ6SKLZA7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b658e83aea40be7074540794aaea021a8575483f5ae4f42a171a716a206b4a2d","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-25T07:31:32Z","title_canon_sha256":"53bb33395b848a6485277dcc6f2b10d263a8c1413ca5a46cc79404dc8b0966a9"},"schema_version":"1.0","source":{"id":"2506.20190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.20190","created_at":"2026-07-05T12:01:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.20190v1","created_at":"2026-07-05T12:01:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20190","created_at":"2026-07-05T12:01:24Z"},{"alias_kind":"pith_short_12","alias_value":"4JSJX2IO5SQ7","created_at":"2026-07-05T12:01:24Z"},{"alias_kind":"pith_short_16","alias_value":"4JSJX2IO5SQ74SMN","created_at":"2026-07-05T12:01:24Z"},{"alias_kind":"pith_short_8","alias_value":"4JSJX2IO","created_at":"2026-07-05T12:01:24Z"}],"graph_snapshots":[{"event_id":"sha256:85d4ce21c56ab80467a0a610a86eb36a32c729084e75364677e889f0a6100735","target":"graph","created_at":"2026-07-05T12:01:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.20190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot multi-speaker text-to-speech (TTS) systems rely on speaker embeddings to synthesize speech in the voice of an unseen speaker, using only a short reference utterance. While many speaker embeddings have been developed for speaker recognition, their relative effectiveness in zero-shot TTS remains underexplored. In this work, we employ a YourTTS-based TTS system to compare three different speaker encoders - YourTTS's original H/ASP encoder, x-vector embeddings, and ECAPA-TDNN embeddings - within an otherwise fixed zero-shot TTS framework. All models were trained on the same dataset of Cz","authors_text":"Jind\\v{r}ich Matou\\v{s}ek, Marie Kune\\v{s}ov\\'a, Zden\\v{e}k Hanzl\\'i\\v{c}ek","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-25T07:31:32Z","title":"An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20190","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db3f700d75d58588ba0bf26c22ec3bf6e37c55a31201a0e4349966977fecc9c3","target":"record","created_at":"2026-07-05T12:01:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b658e83aea40be7074540794aaea021a8575483f5ae4f42a171a716a206b4a2d","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-25T07:31:32Z","title_canon_sha256":"53bb33395b848a6485277dcc6f2b10d263a8c1413ca5a46cc79404dc8b0966a9"},"schema_version":"1.0","source":{"id":"2506.20190","kind":"arxiv","version":1}},"canonical_sha256":"e2649be90eeca1fe498d2633e9297907da781ec5031194aecf095ee4cb829060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2649be90eeca1fe498d2633e9297907da781ec5031194aecf095ee4cb829060","first_computed_at":"2026-07-05T12:01:24.338832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:24.338832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZmrM4ejGDIonRdUBzbAfMmmhryODWN8MMD93G8RTUH8mUoaMwSrhC6ODe/iglq/Bqwv5aKH6D/uXNyx1TuibBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:24.339338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.20190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db3f700d75d58588ba0bf26c22ec3bf6e37c55a31201a0e4349966977fecc9c3","sha256:85d4ce21c56ab80467a0a610a86eb36a32c729084e75364677e889f0a6100735"],"state_sha256":"df0f7b14cc0646e855e3692c42f9389bdd8de7c479c84560826cefd4a7aae2f2"}