{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LG2CFNMFTI7DEIRHAM5QIHJ3EC","short_pith_number":"pith:LG2CFNMF","schema_version":"1.0","canonical_sha256":"59b422b5859a3e322227033b041d3b20b7c4200995f3b714f8ffbadfb45f0ae3","source":{"kind":"arxiv","id":"2202.07273","version":2},"attestation_state":"computed","paper":{"title":"SpeechPainter: Text-conditioned Speech Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Marco Tagliasacchi, Matt Sharifi, Zal\\'an Borsos","submitted_at":"2022-02-15T09:33:30Z","abstract_excerpt":"We propose SpeechPainter, a model for filling in gaps of up to one second in speech samples by leveraging an auxiliary textual input. We demonstrate that the model performs speech inpainting with the appropriate content, while maintaining speaker identity, prosody and recording environment conditions, and generalizing to unseen speakers. Our approach significantly outperforms baselines constructed using adaptive TTS, as judged by human raters in side-by-side preference and MOS tests."},"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":"2202.07273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-02-15T09:33:30Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d260c705c8aceed8eb35a1efbe104115671bd63a590b8f7321792d791002ecae","abstract_canon_sha256":"725de981a4bbc59ccf4f978db695096d35432f8ef4f4b36967911983a8de43d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:01.142008Z","signature_b64":"5fpdBtDGBHM/APB0OALfThNJllY/rOnNxHKJfh1o23L6KEuRGOMkEVefsi1kGvu7gYj3BVfEKuDSrlz/k3BjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b422b5859a3e322227033b041d3b20b7c4200995f3b714f8ffbadfb45f0ae3","last_reissued_at":"2026-07-05T04:10:01.141538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:01.141538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechPainter: Text-conditioned Speech Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Marco Tagliasacchi, Matt Sharifi, Zal\\'an Borsos","submitted_at":"2022-02-15T09:33:30Z","abstract_excerpt":"We propose SpeechPainter, a model for filling in gaps of up to one second in speech samples by leveraging an auxiliary textual input. We demonstrate that the model performs speech inpainting with the appropriate content, while maintaining speaker identity, prosody and recording environment conditions, and generalizing to unseen speakers. Our approach significantly outperforms baselines constructed using adaptive TTS, as judged by human raters in side-by-side preference and MOS tests."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07273","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/2202.07273/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":"2202.07273","created_at":"2026-07-05T04:10:01.141598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07273v2","created_at":"2026-07-05T04:10:01.141598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07273","created_at":"2026-07-05T04:10:01.141598+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG2CFNMFTI7D","created_at":"2026-07-05T04:10:01.141598+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG2CFNMFTI7DEIRH","created_at":"2026-07-05T04:10:01.141598+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG2CFNMF","created_at":"2026-07-05T04:10:01.141598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06424","citing_title":"Multi Codec Discrete Diffusion Model for Text Guided Speech Inpainting and Editing","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC","json":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC.json","graph_json":"https://pith.science/api/pith-number/LG2CFNMFTI7DEIRHAM5QIHJ3EC/graph.json","events_json":"https://pith.science/api/pith-number/LG2CFNMFTI7DEIRHAM5QIHJ3EC/events.json","paper":"https://pith.science/paper/LG2CFNMF"},"agent_actions":{"view_html":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC","download_json":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC.json","view_paper":"https://pith.science/paper/LG2CFNMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07273&json=true","fetch_graph":"https://pith.science/api/pith-number/LG2CFNMFTI7DEIRHAM5QIHJ3EC/graph.json","fetch_events":"https://pith.science/api/pith-number/LG2CFNMFTI7DEIRHAM5QIHJ3EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC/action/storage_attestation","attest_author":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC/action/author_attestation","sign_citation":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC/action/citation_signature","submit_replication":"https://pith.science/pith/LG2CFNMFTI7DEIRHAM5QIHJ3EC/action/replication_record"}},"created_at":"2026-07-05T04:10:01.141598+00:00","updated_at":"2026-07-05T04:10:01.141598+00:00"}