{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7YSKWR6NMSGTD6FHJWA57UAF75","short_pith_number":"pith:7YSKWR6N","schema_version":"1.0","canonical_sha256":"fe24ab47cd648d31f8a74d81dfd005ff56c8170c2bca973994dd375430fe70c9","source":{"kind":"arxiv","id":"2109.05426","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chong Luo, Chuanxin Tang, Dacheng Yin, Wenjun Zeng, Yucheng Zhao, Zhiyuan Zhao","submitted_at":"2021-09-12T04:17:53Z","abstract_excerpt":"Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the input text using a generic text-to-speech (TTS) engine and then transform the voice to the desired voice using voice conversion (VC). A major problem of this framework is that VC is a challenging problem which usually needs a moderate amount of parallel training data to work satisfactorily. In this paper, we propose a one-stage context-aware framework to gen"},"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":"2109.05426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-09-12T04:17:53Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"22b71bc115b41240357fd83aefa4e11ba570fd005f001dba4ee18c5a48cd830e","abstract_canon_sha256":"57da054b34c2a30b8469d7764861b2954c90e8ad145dd73d0079ddbb90ee93f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:38.813475Z","signature_b64":"ee9JtVg/DVs9t247xWDDTuBmDLmQ90UvSHwNBZUqNpCWtMfABuEnQnCoQdFUaXX162CrNUUwY9TQxZdUL1L2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe24ab47cd648d31f8a74d81dfd005ff56c8170c2bca973994dd375430fe70c9","last_reissued_at":"2026-07-05T03:13:38.813054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:38.813054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Text-to-Speech for Text-Based Insertion in Audio Narration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chong Luo, Chuanxin Tang, Dacheng Yin, Wenjun Zeng, Yucheng Zhao, Zhiyuan Zhao","submitted_at":"2021-09-12T04:17:53Z","abstract_excerpt":"Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the input text using a generic text-to-speech (TTS) engine and then transform the voice to the desired voice using voice conversion (VC). A major problem of this framework is that VC is a challenging problem which usually needs a moderate amount of parallel training data to work satisfactorily. In this paper, we propose a one-stage context-aware framework to gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05426","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/2109.05426/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":"2109.05426","created_at":"2026-07-05T03:13:38.813110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05426v1","created_at":"2026-07-05T03:13:38.813110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05426","created_at":"2026-07-05T03:13:38.813110+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YSKWR6NMSGT","created_at":"2026-07-05T03:13:38.813110+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YSKWR6NMSGTD6FH","created_at":"2026-07-05T03:13:38.813110+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YSKWR6N","created_at":"2026-07-05T03:13:38.813110+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/7YSKWR6NMSGTD6FHJWA57UAF75","json":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75.json","graph_json":"https://pith.science/api/pith-number/7YSKWR6NMSGTD6FHJWA57UAF75/graph.json","events_json":"https://pith.science/api/pith-number/7YSKWR6NMSGTD6FHJWA57UAF75/events.json","paper":"https://pith.science/paper/7YSKWR6N"},"agent_actions":{"view_html":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75","download_json":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75.json","view_paper":"https://pith.science/paper/7YSKWR6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05426&json=true","fetch_graph":"https://pith.science/api/pith-number/7YSKWR6NMSGTD6FHJWA57UAF75/graph.json","fetch_events":"https://pith.science/api/pith-number/7YSKWR6NMSGTD6FHJWA57UAF75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75/action/storage_attestation","attest_author":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75/action/author_attestation","sign_citation":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75/action/citation_signature","submit_replication":"https://pith.science/pith/7YSKWR6NMSGTD6FHJWA57UAF75/action/replication_record"}},"created_at":"2026-07-05T03:13:38.813110+00:00","updated_at":"2026-07-05T03:13:38.813110+00:00"}