{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XCRWRD22M7FPFT34JCZ3EHL5QL","short_pith_number":"pith:XCRWRD22","canonical_record":{"source":{"id":"2503.16956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-21T09:02:38Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"title_canon_sha256":"10a1b9cd9d8b98601e37a097fb84fad78d30ce9becb65ca7cd552d6636d5c579","abstract_canon_sha256":"de2379d5b470161fe11318a1f913d5fab53c52dd454c0344ef64d41927edddd8"},"schema_version":"1.0"},"canonical_sha256":"b8a3688f5a67caf2cf7c48b3b21d7d82f16c26e1b3171553e7faa6cbb8b4fa5f","source":{"kind":"arxiv","id":"2503.16956","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16956","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16956v1","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16956","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"XCRWRD22M7FP","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"XCRWRD22M7FPFT34","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"XCRWRD22","created_at":"2026-07-05T10:36:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XCRWRD22M7FPFT34JCZ3EHL5QL","target":"record","payload":{"canonical_record":{"source":{"id":"2503.16956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-21T09:02:38Z","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"title_canon_sha256":"10a1b9cd9d8b98601e37a097fb84fad78d30ce9becb65ca7cd552d6636d5c579","abstract_canon_sha256":"de2379d5b470161fe11318a1f913d5fab53c52dd454c0344ef64d41927edddd8"},"schema_version":"1.0"},"canonical_sha256":"b8a3688f5a67caf2cf7c48b3b21d7d82f16c26e1b3171553e7faa6cbb8b4fa5f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:53.579549Z","signature_b64":"yQcBTLjXowXcn90gn2FO/nLnMH7s55PbM5HyJK+7dekOnuU8loUD4aW9JjeLzwJpfgvcHaka32AJPvwzau0SCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a3688f5a67caf2cf7c48b3b21d7d82f16c26e1b3171553e7faa6cbb8b4fa5f","last_reissued_at":"2026-07-05T10:36:53.579022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:53.579022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.16956","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:36:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSgO4zRE/KExn4wWw2g/S9IvliujG1XERnyE/owUAiiuKDCnWojW94XOEmI2v1j+EbeYcvoQN6zAVBgtih8LCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:52:47.300680Z"},"content_sha256":"53acdd211a3215538ce6a460ac2851157c1278a49d09156fa6f55631cdb444fc","schema_version":"1.0","event_id":"sha256:53acdd211a3215538ce6a460ac2851157c1278a49d09156fa6f55631cdb444fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XCRWRD22M7FPFT34JCZ3EHL5QL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chaeyoung Jung, Jaehun Kim, Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung","submitted_at":"2025-03-21T09:02:38Z","abstract_excerpt":"The objective of this study is to generate high-quality speech from silent talking face videos, a task also known as video-to-speech synthesis. A significant challenge in video-to-speech synthesis lies in the substantial modality gap between silent video and multi-faceted speech. In this paper, we propose a novel video-to-speech system that effectively bridges this modality gap, significantly enhancing the quality of synthesized speech. This is achieved by learning of hierarchical representations from video to speech. Specifically, we gradually transform silent video into acoustic feature spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16956","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/2503.16956/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:36:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HSfz2wmctqvlrG8nnH3mejux536cMXAHjrgPon4oK2j3xTfhQDN/3peE7IQLfcMtC0fflgSljBJVDx0PS8k3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:52:47.301205Z"},"content_sha256":"061545820f0542a528de1922c38331c3fa77ce5ea1e89e671eb31259e32ad4e2","schema_version":"1.0","event_id":"sha256:061545820f0542a528de1922c38331c3fa77ce5ea1e89e671eb31259e32ad4e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCRWRD22M7FPFT34JCZ3EHL5QL/bundle.json","state_url":"https://pith.science/pith/XCRWRD22M7FPFT34JCZ3EHL5QL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCRWRD22M7FPFT34JCZ3EHL5QL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T00:52:47Z","links":{"resolver":"https://pith.science/pith/XCRWRD22M7FPFT34JCZ3EHL5QL","bundle":"https://pith.science/pith/XCRWRD22M7FPFT34JCZ3EHL5QL/bundle.json","state":"https://pith.science/pith/XCRWRD22M7FPFT34JCZ3EHL5QL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCRWRD22M7FPFT34JCZ3EHL5QL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XCRWRD22M7FPFT34JCZ3EHL5QL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"de2379d5b470161fe11318a1f913d5fab53c52dd454c0344ef64d41927edddd8","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-21T09:02:38Z","title_canon_sha256":"10a1b9cd9d8b98601e37a097fb84fad78d30ce9becb65ca7cd552d6636d5c579"},"schema_version":"1.0","source":{"id":"2503.16956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.16956","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2503.16956v1","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16956","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"XCRWRD22M7FP","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"XCRWRD22M7FPFT34","created_at":"2026-07-05T10:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"XCRWRD22","created_at":"2026-07-05T10:36:53Z"}],"graph_snapshots":[{"event_id":"sha256:061545820f0542a528de1922c38331c3fa77ce5ea1e89e671eb31259e32ad4e2","target":"graph","created_at":"2026-07-05T10:36:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.16956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of this study is to generate high-quality speech from silent talking face videos, a task also known as video-to-speech synthesis. A significant challenge in video-to-speech synthesis lies in the substantial modality gap between silent video and multi-faceted speech. In this paper, we propose a novel video-to-speech system that effectively bridges this modality gap, significantly enhancing the quality of synthesized speech. This is achieved by learning of hierarchical representations from video to speech. Specifically, we gradually transform silent video into acoustic feature spac","authors_text":"Chaeyoung Jung, Jaehun Kim, Jeongsoo Choi, Ji-Hoon Kim, Joon Son Chung","cross_cats":["cs.AI","cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-21T09:02:38Z","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16956","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:53acdd211a3215538ce6a460ac2851157c1278a49d09156fa6f55631cdb444fc","target":"record","created_at":"2026-07-05T10:36:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"de2379d5b470161fe11318a1f913d5fab53c52dd454c0344ef64d41927edddd8","cross_cats_sorted":["cs.AI","cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-03-21T09:02:38Z","title_canon_sha256":"10a1b9cd9d8b98601e37a097fb84fad78d30ce9becb65ca7cd552d6636d5c579"},"schema_version":"1.0","source":{"id":"2503.16956","kind":"arxiv","version":1}},"canonical_sha256":"b8a3688f5a67caf2cf7c48b3b21d7d82f16c26e1b3171553e7faa6cbb8b4fa5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8a3688f5a67caf2cf7c48b3b21d7d82f16c26e1b3171553e7faa6cbb8b4fa5f","first_computed_at":"2026-07-05T10:36:53.579022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:53.579022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yQcBTLjXowXcn90gn2FO/nLnMH7s55PbM5HyJK+7dekOnuU8loUD4aW9JjeLzwJpfgvcHaka32AJPvwzau0SCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:53.579549Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.16956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53acdd211a3215538ce6a460ac2851157c1278a49d09156fa6f55631cdb444fc","sha256:061545820f0542a528de1922c38331c3fa77ce5ea1e89e671eb31259e32ad4e2"],"state_sha256":"3b51a798307ca2862385c1ba6237a6710a71fc9dbffab6b949aa0d5bd82df13d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDF9qYp4BArjEYrz2Z2Ph3cL5Bb8TwaltJio1hL1BGU+l0z1OiFasNXMYC5GJa9RBMtSept3Qb3D7f6LvmvjCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:52:47.304606Z","bundle_sha256":"90a97db076bc6c47c6bc8fdeaac236006974972f708288603da38edf2cac90a2"}}