{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CUJFI7WEWQ6MUN57EIJUVW2OFS","short_pith_number":"pith:CUJFI7WE","schema_version":"1.0","canonical_sha256":"1512547ec4b43cca37bf22134adb4e2cbd321635d736da8472d3b943989f9988","source":{"kind":"arxiv","id":"2306.16083","version":1},"attestation_state":"computed","paper":{"title":"UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heeseung Kim, Jiheum Yeom, Sungroh Yoon, Sungwon Kim","submitted_at":"2023-06-28T10:30:39Z","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"},"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":"2306.16083","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T10:30:39Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"75cfe323f3064e996d87e03af9d55bee13fde39a4b951c757072f0970b677933","abstract_canon_sha256":"db8c0e4eb8af3871a8390e2ba9698fda1f1775ad6bcf623b826efa335e1a8f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:48.643869Z","signature_b64":"Np0A8fh8I40+itEXUuOIb8LJYNa4oovp0X+9dPbJG7nng1r6Aplan3owRtp/7u0Y9i3ojU+uYI7Xcv3cR4APCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1512547ec4b43cca37bf22134adb4e2cbd321635d736da8472d3b943989f9988","last_reissued_at":"2026-07-05T06:25:48.643474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:48.643474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heeseung Kim, Jiheum Yeom, Sungroh Yoon, Sungwon Kim","submitted_at":"2023-06-28T10:30:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16083","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/2306.16083/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":"2306.16083","created_at":"2026-07-05T06:25:48.643538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16083v1","created_at":"2026-07-05T06:25:48.643538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16083","created_at":"2026-07-05T06:25:48.643538+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUJFI7WEWQ6M","created_at":"2026-07-05T06:25:48.643538+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUJFI7WEWQ6MUN57","created_at":"2026-07-05T06:25:48.643538+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUJFI7WE","created_at":"2026-07-05T06:25:48.643538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00503","citing_title":"Entropy-based Coarse and Compressed Semantic Speech Representation Learning","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS","json":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS.json","graph_json":"https://pith.science/api/pith-number/CUJFI7WEWQ6MUN57EIJUVW2OFS/graph.json","events_json":"https://pith.science/api/pith-number/CUJFI7WEWQ6MUN57EIJUVW2OFS/events.json","paper":"https://pith.science/paper/CUJFI7WE"},"agent_actions":{"view_html":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS","download_json":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS.json","view_paper":"https://pith.science/paper/CUJFI7WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16083&json=true","fetch_graph":"https://pith.science/api/pith-number/CUJFI7WEWQ6MUN57EIJUVW2OFS/graph.json","fetch_events":"https://pith.science/api/pith-number/CUJFI7WEWQ6MUN57EIJUVW2OFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS/action/storage_attestation","attest_author":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS/action/author_attestation","sign_citation":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS/action/citation_signature","submit_replication":"https://pith.science/pith/CUJFI7WEWQ6MUN57EIJUVW2OFS/action/replication_record"}},"created_at":"2026-07-05T06:25:48.643538+00:00","updated_at":"2026-07-05T06:25:48.643538+00:00"}