{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SU46RERG3P2XK2BU7C2BAMVNRG","short_pith_number":"pith:SU46RERG","schema_version":"1.0","canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","source":{"kind":"arxiv","id":"2606.20266","version":1},"attestation_state":"computed","paper":{"title":"Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chang D. Yoo, Eunseop Yoon, Hee Suk Yoon, Mark Hasegawa-Johnson, SooHwan Eom","submitted_at":"2026-06-18T14:14:14Z","abstract_excerpt":"Recent flow-matching text-to-speech (TTS) models, such as F5-TTS, rely on a reference transcript at inference time, obtained from an external ASR system. This dependency makes zero-shot TTS brittle for accented or dysarthric speakers, precisely the scenarios where it is most needed. Moreover, we find that text-based reference conditioning can propagate atypical acoustic patterns from atypical speech into synthesis, even when ground-truth transcripts are available. To address this, we propose RTFree-F5, which replaces the reference transcript with continuous self-supervised speech representatio"},"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":"2606.20266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T14:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"d0cc2f5c8a41c099c968917e38063c0231f2f54a9491fc6f51ab63cd4f408c0e","abstract_canon_sha256":"c085c1fef3f982a8cf2c83f8cfcfac6dd584aa8ce7dfe7dbb6299786a05718fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:07.306130Z","signature_b64":"FufvHFFK5oC57tQ03R72m4+liuk8aawuqLoHvx+BFToseUxlb5sA/1J3z6S5kHZCsVI1U5KrgoGgfS2kpe/sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","last_reissued_at":"2026-06-19T16:13:07.305783Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:07.305783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chang D. Yoo, Eunseop Yoon, Hee Suk Yoon, Mark Hasegawa-Johnson, SooHwan Eom","submitted_at":"2026-06-18T14:14:14Z","abstract_excerpt":"Recent flow-matching text-to-speech (TTS) models, such as F5-TTS, rely on a reference transcript at inference time, obtained from an external ASR system. This dependency makes zero-shot TTS brittle for accented or dysarthric speakers, precisely the scenarios where it is most needed. Moreover, we find that text-based reference conditioning can propagate atypical acoustic patterns from atypical speech into synthesis, even when ground-truth transcripts are available. To address this, we propose RTFree-F5, which replaces the reference transcript with continuous self-supervised speech representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20266","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/2606.20266/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":"2606.20266","created_at":"2026-06-19T16:13:07.305845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20266v1","created_at":"2026-06-19T16:13:07.305845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20266","created_at":"2026-06-19T16:13:07.305845+00:00"},{"alias_kind":"pith_short_12","alias_value":"SU46RERG3P2X","created_at":"2026-06-19T16:13:07.305845+00:00"},{"alias_kind":"pith_short_16","alias_value":"SU46RERG3P2XK2BU","created_at":"2026-06-19T16:13:07.305845+00:00"},{"alias_kind":"pith_short_8","alias_value":"SU46RERG","created_at":"2026-06-19T16:13:07.305845+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/SU46RERG3P2XK2BU7C2BAMVNRG","json":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG.json","graph_json":"https://pith.science/api/pith-number/SU46RERG3P2XK2BU7C2BAMVNRG/graph.json","events_json":"https://pith.science/api/pith-number/SU46RERG3P2XK2BU7C2BAMVNRG/events.json","paper":"https://pith.science/paper/SU46RERG"},"agent_actions":{"view_html":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG","download_json":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG.json","view_paper":"https://pith.science/paper/SU46RERG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20266&json=true","fetch_graph":"https://pith.science/api/pith-number/SU46RERG3P2XK2BU7C2BAMVNRG/graph.json","fetch_events":"https://pith.science/api/pith-number/SU46RERG3P2XK2BU7C2BAMVNRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/action/storage_attestation","attest_author":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/action/author_attestation","sign_citation":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/action/citation_signature","submit_replication":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/action/replication_record"}},"created_at":"2026-06-19T16:13:07.305845+00:00","updated_at":"2026-06-19T16:13:07.305845+00:00"}