{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XWBRKILEFP27BXOX4RN6765BON","short_pith_number":"pith:XWBRKILE","schema_version":"1.0","canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","source":{"kind":"arxiv","id":"2505.19384","version":1},"attestation_state":"computed","paper":{"title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jungjun Kim, Seokgi Lee","submitted_at":"2025-05-26T00:58:16Z","abstract_excerpt":"We present the gradual style adaptor TTS (GSA-TTS) with a novel style encoder that gradually encodes speaking styles from an acoustic reference for zero-shot speech synthesis. GSA first captures the local style of each semantic sound unit. Then the local styles are combined by self-attention to obtain a global style condition. This semantic and hierarchical encoding strategy provides a robust and rich style representation for an acoustic model. We test GSA-TTS on unseen speakers and obtain promising results regarding naturalness, speaker similarity, and intelligibility. Additionally, we explor"},"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":"2505.19384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T00:58:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31d068e1f31d44abca50de49522e5ebd2f6068ca25a992b0b22fe618710c6122","abstract_canon_sha256":"d9eb774777950961c24d974df11d4a2b9a9b99a44c8f128ef2a9f4bf5ed01243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:29.440501Z","signature_b64":"C6WwpHJF2pP04PtMgbb+gFUu/g+70FBO+Z3Wj6Sa7KoEHx5BLn3BDq2x4/zFYH9QOw9NUO5a3iqkfFrZPFu+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","last_reissued_at":"2026-07-05T11:09:29.440095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:29.440095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jungjun Kim, Seokgi Lee","submitted_at":"2025-05-26T00:58:16Z","abstract_excerpt":"We present the gradual style adaptor TTS (GSA-TTS) with a novel style encoder that gradually encodes speaking styles from an acoustic reference for zero-shot speech synthesis. GSA first captures the local style of each semantic sound unit. Then the local styles are combined by self-attention to obtain a global style condition. This semantic and hierarchical encoding strategy provides a robust and rich style representation for an acoustic model. We test GSA-TTS on unseen speakers and obtain promising results regarding naturalness, speaker similarity, and intelligibility. Additionally, we explor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19384","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/2505.19384/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":"2505.19384","created_at":"2026-07-05T11:09:29.440153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19384v1","created_at":"2026-07-05T11:09:29.440153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19384","created_at":"2026-07-05T11:09:29.440153+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWBRKILEFP27","created_at":"2026-07-05T11:09:29.440153+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWBRKILEFP27BXOX","created_at":"2026-07-05T11:09:29.440153+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWBRKILE","created_at":"2026-07-05T11:09:29.440153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19384","citing_title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON","json":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON.json","graph_json":"https://pith.science/api/pith-number/XWBRKILEFP27BXOX4RN6765BON/graph.json","events_json":"https://pith.science/api/pith-number/XWBRKILEFP27BXOX4RN6765BON/events.json","paper":"https://pith.science/paper/XWBRKILE"},"agent_actions":{"view_html":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON","download_json":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON.json","view_paper":"https://pith.science/paper/XWBRKILE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19384&json=true","fetch_graph":"https://pith.science/api/pith-number/XWBRKILEFP27BXOX4RN6765BON/graph.json","fetch_events":"https://pith.science/api/pith-number/XWBRKILEFP27BXOX4RN6765BON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/action/storage_attestation","attest_author":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/action/author_attestation","sign_citation":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/action/citation_signature","submit_replication":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/action/replication_record"}},"created_at":"2026-07-05T11:09:29.440153+00:00","updated_at":"2026-07-05T11:09:29.440153+00:00"}