{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GOZBRYJWPAGF2Q67LFUFS4LVFP","short_pith_number":"pith:GOZBRYJW","schema_version":"1.0","canonical_sha256":"33b218e136780c5d43df59685971752bf5a62a10643ba641fda8f36d895e2216","source":{"kind":"arxiv","id":"2210.16045","version":1},"attestation_state":"computed","paper":{"title":"Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jason Fong, Jilong Wu, Prabhav Agrawal, Qing He, Thilo K\\\"ohler, Vimal Manohar, Yun Wang","submitted_at":"2022-10-28T10:31:44Z","abstract_excerpt":"Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording. Recent work has used neural models to produce edited speech that is similar to the original speech in terms of clarity, speaker identity, and prosody. However, one limitation of prior work is the usage of finetuning to optimise performance: this requires further model training on data from the target speaker, which is a costly process that may incorporate potentially sensitive data into server-side models. In contrast, this work focuses on the zero-shot approach wh"},"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":"2210.16045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-10-28T10:31:44Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"6d9f1d456541af23791282e7d195f7f06292d59f342073e90eebc7a3c5481c5d","abstract_canon_sha256":"7aef2823b2bb146d1b92cc519153149a2cae1f72f81b09370af11953df308ae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:30.013296Z","signature_b64":"IjZ+udiRJ2LoJYN1Wa81dt7KCkgYlzsja1o0pTCevhjbqIjL8WYS5drJ6WbvUjTg8djlDPsHTpm/kgT8RXkVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33b218e136780c5d43df59685971752bf5a62a10643ba641fda8f36d895e2216","last_reissued_at":"2026-07-05T05:11:30.012955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:30.012955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jason Fong, Jilong Wu, Prabhav Agrawal, Qing He, Thilo K\\\"ohler, Vimal Manohar, Yun Wang","submitted_at":"2022-10-28T10:31:44Z","abstract_excerpt":"Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording. Recent work has used neural models to produce edited speech that is similar to the original speech in terms of clarity, speaker identity, and prosody. However, one limitation of prior work is the usage of finetuning to optimise performance: this requires further model training on data from the target speaker, which is a costly process that may incorporate potentially sensitive data into server-side models. In contrast, this work focuses on the zero-shot approach wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16045","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/2210.16045/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":"2210.16045","created_at":"2026-07-05T05:11:30.013017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16045v1","created_at":"2026-07-05T05:11:30.013017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16045","created_at":"2026-07-05T05:11:30.013017+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOZBRYJWPAGF","created_at":"2026-07-05T05:11:30.013017+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOZBRYJWPAGF2Q67","created_at":"2026-07-05T05:11:30.013017+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOZBRYJW","created_at":"2026-07-05T05:11:30.013017+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/GOZBRYJWPAGF2Q67LFUFS4LVFP","json":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP.json","graph_json":"https://pith.science/api/pith-number/GOZBRYJWPAGF2Q67LFUFS4LVFP/graph.json","events_json":"https://pith.science/api/pith-number/GOZBRYJWPAGF2Q67LFUFS4LVFP/events.json","paper":"https://pith.science/paper/GOZBRYJW"},"agent_actions":{"view_html":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP","download_json":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP.json","view_paper":"https://pith.science/paper/GOZBRYJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16045&json=true","fetch_graph":"https://pith.science/api/pith-number/GOZBRYJWPAGF2Q67LFUFS4LVFP/graph.json","fetch_events":"https://pith.science/api/pith-number/GOZBRYJWPAGF2Q67LFUFS4LVFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP/action/storage_attestation","attest_author":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP/action/author_attestation","sign_citation":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP/action/citation_signature","submit_replication":"https://pith.science/pith/GOZBRYJWPAGF2Q67LFUFS4LVFP/action/replication_record"}},"created_at":"2026-07-05T05:11:30.013017+00:00","updated_at":"2026-07-05T05:11:30.013017+00:00"}