{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4JSJX2IO5SQ74SMNEYZ6SKLZA7","short_pith_number":"pith:4JSJX2IO","canonical_record":{"source":{"id":"2506.20190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-25T07:31:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"53bb33395b848a6485277dcc6f2b10d263a8c1413ca5a46cc79404dc8b0966a9","abstract_canon_sha256":"b658e83aea40be7074540794aaea021a8575483f5ae4f42a171a716a206b4a2d"},"schema_version":"1.0"},"canonical_sha256":"e2649be90eeca1fe498d2633e9297907da781ec5031194aecf095ee4cb829060","source":{"kind":"arxiv","id":"2506.20190","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4JSJX2IO5SQ74SMNEYZ6SKLZA7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.20190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-06-25T07:31:32Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"53bb33395b848a6485277dcc6f2b10d263a8c1413ca5a46cc79404dc8b0966a9","abstract_canon_sha256":"b658e83aea40be7074540794aaea021a8575483f5ae4f42a171a716a206b4a2d"},"schema_version":"1.0"},"canonical_sha256":"e2649be90eeca1fe498d2633e9297907da781ec5031194aecf095ee4cb829060","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:24.339338Z","signature_b64":"ZmrM4ejGDIonRdUBzbAfMmmhryODWN8MMD93G8RTUH8mUoaMwSrhC6ODe/iglq/Bqwv5aKH6D/uXNyx1TuibBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2649be90eeca1fe498d2633e9297907da781ec5031194aecf095ee4cb829060","last_reissued_at":"2026-07-05T12:01:24.338832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:24.338832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.20190","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oUN+UxayCcylsvVge0eoBV+0E+T70f0LO2vVy0RihwTyvt1fcYwxc5ueSMj1Vlrte31mXYBSQCeDTbZwnm/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:11:13.520372Z"},"content_sha256":"db3f700d75d58588ba0bf26c22ec3bf6e37c55a31201a0e4349966977fecc9c3","schema_version":"1.0","event_id":"sha256:db3f700d75d58588ba0bf26c22ec3bf6e37c55a31201a0e4349966977fecc9c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4JSJX2IO5SQ74SMNEYZ6SKLZA7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Exploration of ECAPA-TDNN and x-vector Speaker Representations in Zero-shot Multi-speaker TTS","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","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","submitted_at":"2025-06-25T07:31:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20190","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/2506.20190/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:01:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdL6+4i7MVzMyoExakdXVfUpmMSHibqXYzByQAoxyQXSh2vFF8OE2YVAKeNsSAyK77vKn1u6Y8vKPxljnAAADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:11:13.521059Z"},"content_sha256":"85d4ce21c56ab80467a0a610a86eb36a32c729084e75364677e889f0a6100735","schema_version":"1.0","event_id":"sha256:85d4ce21c56ab80467a0a610a86eb36a32c729084e75364677e889f0a6100735"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/bundle.json","state_url":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T11:11:13Z","links":{"resolver":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7","bundle":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/bundle.json","state":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFXwoDFQXOn8acdwDLvfS9mxEREIiOX82RENVA2HCMct4W2YIwBG0+tEeuieF59Hr1KpkRb8Hkalc8k2Vz0ZCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:11:13.526355Z","bundle_sha256":"256a9ff89fbeb8cb616890298b24ca2a31c975bf38eafd113987b6ffa4756bb7"}}