{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZNTYPDPY3XDER6MVXJ6KPDXRQK","short_pith_number":"pith:ZNTYPDPY","schema_version":"1.0","canonical_sha256":"cb67878df8ddc648f995ba7ca78ef182b2a1a2454a881d68014fdecb9eb9f6bc","source":{"kind":"arxiv","id":"2308.07787","version":1},"attestation_state":"computed","paper":{"title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jeongsoo Choi, Joanna Hong, Yong Man Ro","submitted_at":"2023-08-15T14:07:41Z","abstract_excerpt":"Recent research has demonstrated impressive results in video-to-speech synthesis which involves reconstructing speech solely from visual input. However, previous works have struggled to accurately synthesize speech due to a lack of sufficient guidance for the model to infer the correct content with the appropriate sound. To resolve the issue, they have adopted an extra speaker embedding as a speaking style guidance from a reference auditory information. Nevertheless, it is not always possible to obtain the audio information from the corresponding video input, especially during the inference ti"},"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":"2308.07787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-15T14:07:41Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"7d478e55b31630e52b20582bd0b45848083353ef7bcae8c651318bab349ba6b3","abstract_canon_sha256":"89ae730f2fedf5aa2f01ca5a9c2b586d41edb60566e525747dc40cedba8e1e87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:31.351311Z","signature_b64":"KxCaoKqh1ghH3Gw8jX8qqqmKppQRNrmFQfNcKEN3gDnW/tHhcfYI6vhaRQxqOdJ2tlT5NQ9d9OquAc2GGgNlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb67878df8ddc648f995ba7ca78ef182b2a1a2454a881d68014fdecb9eb9f6bc","last_reissued_at":"2026-07-05T06:41:31.350839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:31.350839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jeongsoo Choi, Joanna Hong, Yong Man Ro","submitted_at":"2023-08-15T14:07:41Z","abstract_excerpt":"Recent research has demonstrated impressive results in video-to-speech synthesis which involves reconstructing speech solely from visual input. However, previous works have struggled to accurately synthesize speech due to a lack of sufficient guidance for the model to infer the correct content with the appropriate sound. To resolve the issue, they have adopted an extra speaker embedding as a speaking style guidance from a reference auditory information. Nevertheless, it is not always possible to obtain the audio information from the corresponding video input, especially during the inference ti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07787","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/2308.07787/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":"2308.07787","created_at":"2026-07-05T06:41:31.350903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07787v1","created_at":"2026-07-05T06:41:31.350903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07787","created_at":"2026-07-05T06:41:31.350903+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNTYPDPY3XDE","created_at":"2026-07-05T06:41:31.350903+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNTYPDPY3XDER6MV","created_at":"2026-07-05T06:41:31.350903+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNTYPDPY","created_at":"2026-07-05T06:41:31.350903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00498","citing_title":"MuteSwap: Visual-informed Silent Video Identity Conversion","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK","json":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK.json","graph_json":"https://pith.science/api/pith-number/ZNTYPDPY3XDER6MVXJ6KPDXRQK/graph.json","events_json":"https://pith.science/api/pith-number/ZNTYPDPY3XDER6MVXJ6KPDXRQK/events.json","paper":"https://pith.science/paper/ZNTYPDPY"},"agent_actions":{"view_html":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK","download_json":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK.json","view_paper":"https://pith.science/paper/ZNTYPDPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07787&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNTYPDPY3XDER6MVXJ6KPDXRQK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNTYPDPY3XDER6MVXJ6KPDXRQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK/action/storage_attestation","attest_author":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK/action/author_attestation","sign_citation":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK/action/citation_signature","submit_replication":"https://pith.science/pith/ZNTYPDPY3XDER6MVXJ6KPDXRQK/action/replication_record"}},"created_at":"2026-07-05T06:41:31.350903+00:00","updated_at":"2026-07-05T06:41:31.350903+00:00"}