{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JFNCGBBKGW6PUPV4HCZEQORIIU","short_pith_number":"pith:JFNCGBBK","schema_version":"1.0","canonical_sha256":"495a23042a35bcfa3ebc38b2483a28450fc1b9addd30d14fa94e91e25ef20ef9","source":{"kind":"arxiv","id":"2206.02246","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Alon Levkovitch, Eliya Nachmani, Lior Wolf","submitted_at":"2022-06-05T19:45:29Z","abstract_excerpt":"We present a novel way of conditioning a pretrained denoising diffusion speech model to produce speech in the voice of a novel person unseen during training. The method requires a short (~3 seconds) sample from the target person, and generation is steered at inference time, without any training steps. At the heart of the method lies a sampling process that combines the estimation of the denoising model with a low-pass version of the new speaker's sample. The objective and subjective evaluations show that our sampling method can generate a voice similar to that of the target speaker in terms of"},"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":"2206.02246","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-06-05T19:45:29Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"214afa373588e8e32619cb0284130ecb6456fd32acfae442bf0045f414452fd8","abstract_canon_sha256":"a36b7463debb9a8ef2fd1f12ed23a61784910cfc2929918eb25061c473c92b0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:04.702020Z","signature_b64":"ufiMwStzcayiSX1XEZo+QWgoTMbGX6JtT1nwNOvkauTWesqSdonS8t/SzI36s/qfvtslXu1shqeKx0WwKZZhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"495a23042a35bcfa3ebc38b2483a28450fc1b9addd30d14fa94e91e25ef20ef9","last_reissued_at":"2026-07-05T04:34:04.701544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:04.701544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Alon Levkovitch, Eliya Nachmani, Lior Wolf","submitted_at":"2022-06-05T19:45:29Z","abstract_excerpt":"We present a novel way of conditioning a pretrained denoising diffusion speech model to produce speech in the voice of a novel person unseen during training. The method requires a short (~3 seconds) sample from the target person, and generation is steered at inference time, without any training steps. At the heart of the method lies a sampling process that combines the estimation of the denoising model with a low-pass version of the new speaker's sample. The objective and subjective evaluations show that our sampling method can generate a voice similar to that of the target speaker in terms of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02246","kind":"arxiv","version":2},"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/2206.02246/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":"2206.02246","created_at":"2026-07-05T04:34:04.701601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02246v2","created_at":"2026-07-05T04:34:04.701601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02246","created_at":"2026-07-05T04:34:04.701601+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFNCGBBKGW6P","created_at":"2026-07-05T04:34:04.701601+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFNCGBBKGW6PUPV4","created_at":"2026-07-05T04:34:04.701601+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFNCGBBK","created_at":"2026-07-05T04:34:04.701601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU","json":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU.json","graph_json":"https://pith.science/api/pith-number/JFNCGBBKGW6PUPV4HCZEQORIIU/graph.json","events_json":"https://pith.science/api/pith-number/JFNCGBBKGW6PUPV4HCZEQORIIU/events.json","paper":"https://pith.science/paper/JFNCGBBK"},"agent_actions":{"view_html":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU","download_json":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU.json","view_paper":"https://pith.science/paper/JFNCGBBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02246&json=true","fetch_graph":"https://pith.science/api/pith-number/JFNCGBBKGW6PUPV4HCZEQORIIU/graph.json","fetch_events":"https://pith.science/api/pith-number/JFNCGBBKGW6PUPV4HCZEQORIIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU/action/storage_attestation","attest_author":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU/action/author_attestation","sign_citation":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU/action/citation_signature","submit_replication":"https://pith.science/pith/JFNCGBBKGW6PUPV4HCZEQORIIU/action/replication_record"}},"created_at":"2026-07-05T04:34:04.701601+00:00","updated_at":"2026-07-05T04:34:04.701601+00:00"}