{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CUJFI7WEWQ6MUN57EIJUVW2OFS","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":"db8c0e4eb8af3871a8390e2ba9698fda1f1775ad6bcf623b826efa335e1a8f8a","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T10:30:39Z","title_canon_sha256":"75cfe323f3064e996d87e03af9d55bee13fde39a4b951c757072f0970b677933"},"schema_version":"1.0","source":{"id":"2306.16083","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.16083","created_at":"2026-07-05T06:25:48Z"},{"alias_kind":"arxiv_version","alias_value":"2306.16083v1","created_at":"2026-07-05T06:25:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16083","created_at":"2026-07-05T06:25:48Z"},{"alias_kind":"pith_short_12","alias_value":"CUJFI7WEWQ6M","created_at":"2026-07-05T06:25:48Z"},{"alias_kind":"pith_short_16","alias_value":"CUJFI7WEWQ6MUN57","created_at":"2026-07-05T06:25:48Z"},{"alias_kind":"pith_short_8","alias_value":"CUJFI7WE","created_at":"2026-07-05T06:25:48Z"}],"graph_snapshots":[{"event_id":"sha256:8653bd9be92d5ec19573cd011d7d63d4904e1c8420d0de8ef038486bd3b70272","target":"graph","created_at":"2026-07-05T06:25:48Z","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/2306.16083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose UnitSpeech, a speaker-adaptive speech synthesis method that fine-tunes a diffusion-based text-to-speech (TTS) model using minimal untranscribed data. To achieve this, we use the self-supervised unit representation as a pseudo transcript and integrate the unit encoder into the pre-trained TTS model. We train the unit encoder to provide speech content to the diffusion-based decoder and then fine-tune the decoder for speaker adaptation to the reference speaker using a single $<$unit, speech$>$ pair. UnitSpeech performs speech synthesis tasks such as TTS and voice conversion (VC) in a p","authors_text":"Heeseung Kim, Jiheum Yeom, Sungroh Yoon, Sungwon Kim","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T10:30:39Z","title":"UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16083","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":"sha256:1733c8ce4b6808b2e5b1053c6a5465bbba303474f8a3d1a5dcc759eed8f9d403","target":"record","created_at":"2026-07-05T06:25:48Z","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":"db8c0e4eb8af3871a8390e2ba9698fda1f1775ad6bcf623b826efa335e1a8f8a","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T10:30:39Z","title_canon_sha256":"75cfe323f3064e996d87e03af9d55bee13fde39a4b951c757072f0970b677933"},"schema_version":"1.0","source":{"id":"2306.16083","kind":"arxiv","version":1}},"canonical_sha256":"1512547ec4b43cca37bf22134adb4e2cbd321635d736da8472d3b943989f9988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1512547ec4b43cca37bf22134adb4e2cbd321635d736da8472d3b943989f9988","first_computed_at":"2026-07-05T06:25:48.643474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:25:48.643474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Np0A8fh8I40+itEXUuOIb8LJYNa4oovp0X+9dPbJG7nng1r6Aplan3owRtp/7u0Y9i3ojU+uYI7Xcv3cR4APCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:25:48.643869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.16083","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1733c8ce4b6808b2e5b1053c6a5465bbba303474f8a3d1a5dcc759eed8f9d403","sha256:8653bd9be92d5ec19573cd011d7d63d4904e1c8420d0de8ef038486bd3b70272"],"state_sha256":"7e2f9df524fa09e0a0a4a8135ddd4584634b6294e0691c99971b8ea109881d14"}