{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4JSJX2IO5SQ74SMNEYZ6SKLZA7","short_pith_number":"pith:4JSJX2IO","schema_version":"1.0","canonical_sha256":"e2649be90eeca1fe498d2633e9297907da781ec5031194aecf095ee4cb829060","source":{"kind":"arxiv","id":"2506.20190","version":1},"attestation_state":"computed","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"},"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":"2506.20190","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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.20190","created_at":"2026-07-05T12:01:24.338893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20190v1","created_at":"2026-07-05T12:01:24.338893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20190","created_at":"2026-07-05T12:01:24.338893+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JSJX2IO5SQ7","created_at":"2026-07-05T12:01:24.338893+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JSJX2IO5SQ74SMN","created_at":"2026-07-05T12:01:24.338893+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JSJX2IO","created_at":"2026-07-05T12:01:24.338893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7","json":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7.json","graph_json":"https://pith.science/api/pith-number/4JSJX2IO5SQ74SMNEYZ6SKLZA7/graph.json","events_json":"https://pith.science/api/pith-number/4JSJX2IO5SQ74SMNEYZ6SKLZA7/events.json","paper":"https://pith.science/paper/4JSJX2IO"},"agent_actions":{"view_html":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7","download_json":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7.json","view_paper":"https://pith.science/paper/4JSJX2IO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20190&json=true","fetch_graph":"https://pith.science/api/pith-number/4JSJX2IO5SQ74SMNEYZ6SKLZA7/graph.json","fetch_events":"https://pith.science/api/pith-number/4JSJX2IO5SQ74SMNEYZ6SKLZA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/action/storage_attestation","attest_author":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/action/author_attestation","sign_citation":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/action/citation_signature","submit_replication":"https://pith.science/pith/4JSJX2IO5SQ74SMNEYZ6SKLZA7/action/replication_record"}},"created_at":"2026-07-05T12:01:24.338893+00:00","updated_at":"2026-07-05T12:01:24.338893+00:00"}