{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZO3NHN32OPN4FGKUMNRZ43B34D","short_pith_number":"pith:ZO3NHN32","canonical_record":{"source":{"id":"1701.00495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-02T19:00:22Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7ec4283314fddab4b94320735e891370758bb205a040e45ad3d7dca7ebc2df14","abstract_canon_sha256":"4c3536f1e0c2159dbc14502c7db5920ed6e9fcb354cb8bae18b9301e6c81c458"},"schema_version":"1.0"},"canonical_sha256":"cbb6d3b77a73dbc2995463639e6c3be0e0cb6dd4e50eaf244ed9699c7caaec88","source":{"kind":"arxiv","id":"1701.00495","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00495","created_at":"2026-05-18T00:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00495v2","created_at":"2026-05-18T00:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00495","created_at":"2026-05-18T00:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZO3NHN32OPN4","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZO3NHN32OPN4FGKU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZO3NHN32","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZO3NHN32OPN4FGKUMNRZ43B34D","target":"record","payload":{"canonical_record":{"source":{"id":"1701.00495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-02T19:00:22Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7ec4283314fddab4b94320735e891370758bb205a040e45ad3d7dca7ebc2df14","abstract_canon_sha256":"4c3536f1e0c2159dbc14502c7db5920ed6e9fcb354cb8bae18b9301e6c81c458"},"schema_version":"1.0"},"canonical_sha256":"cbb6d3b77a73dbc2995463639e6c3be0e0cb6dd4e50eaf244ed9699c7caaec88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:11.866257Z","signature_b64":"KXve4fVb6zSNWqUNCWYhCpC8+1YFVx8GiQUqoX6lqrkV2isusGPZbfIFIrL43MsBj1kKy0BsLijVRoJevudDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbb6d3b77a73dbc2995463639e6c3be0e0cb6dd4e50eaf244ed9699c7caaec88","last_reissued_at":"2026-05-18T00:53:11.865802Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:11.865802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1701.00495","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdPLLNf6YvPSChZPAQAJ0v2f2lVvkb6WIy1R5Ks0A1HqPc4qmkFDXCweOUWCbv1Hd56eU44/ja/jsg9WUGq+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:02:14.371157Z"},"content_sha256":"e50db9ed4f9454ee5c41db8adbc4ca03b59fe64c62d492070b68b089ef7f8f41","schema_version":"1.0","event_id":"sha256:e50db9ed4f9454ee5c41db8adbc4ca03b59fe64c62d492070b68b089ef7f8f41"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZO3NHN32OPN4FGKUMNRZ43B34D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vid2speech: Speech Reconstruction from Silent Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Ariel Ephrat, Shmuel Peleg","submitted_at":"2017-01-02T19:00:22Z","abstract_excerpt":"Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames of a speaking person. The proposed CNN generates sound features for each frame based on its neighboring frames. Waveforms are then synthesized from the learned speech features to produce intelligible speech. We show that by leveraging the automatic feature learning capabilities of a CNN, we can obtain state-of-the-art word intelligibility on the GRID dataset,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00495","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":""},"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":"2026-05-18T00:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiUD9jcYhRp79d16aYxDyJ2NjoUgggQuJSX/mpmCN4VG3+YE6U0+5bYTZHgItv3lJwFNVIkoKRVnNLneNNWpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:02:14.371520Z"},"content_sha256":"3d5f4aa24217e83b4e3b406f466ab47143881968cb34077700c8d88a53034636","schema_version":"1.0","event_id":"sha256:3d5f4aa24217e83b4e3b406f466ab47143881968cb34077700c8d88a53034636"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZO3NHN32OPN4FGKUMNRZ43B34D/bundle.json","state_url":"https://pith.science/pith/ZO3NHN32OPN4FGKUMNRZ43B34D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZO3NHN32OPN4FGKUMNRZ43B34D/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":"2026-05-28T13:02:14Z","links":{"resolver":"https://pith.science/pith/ZO3NHN32OPN4FGKUMNRZ43B34D","bundle":"https://pith.science/pith/ZO3NHN32OPN4FGKUMNRZ43B34D/bundle.json","state":"https://pith.science/pith/ZO3NHN32OPN4FGKUMNRZ43B34D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZO3NHN32OPN4FGKUMNRZ43B34D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZO3NHN32OPN4FGKUMNRZ43B34D","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":"4c3536f1e0c2159dbc14502c7db5920ed6e9fcb354cb8bae18b9301e6c81c458","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-02T19:00:22Z","title_canon_sha256":"7ec4283314fddab4b94320735e891370758bb205a040e45ad3d7dca7ebc2df14"},"schema_version":"1.0","source":{"id":"1701.00495","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.00495","created_at":"2026-05-18T00:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"1701.00495v2","created_at":"2026-05-18T00:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.00495","created_at":"2026-05-18T00:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"ZO3NHN32OPN4","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZO3NHN32OPN4FGKU","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZO3NHN32","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:3d5f4aa24217e83b4e3b406f466ab47143881968cb34077700c8d88a53034636","target":"graph","created_at":"2026-05-18T00:53:11Z","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"},"paper":{"abstract_excerpt":"Speechreading is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible acoustic speech signal from silent video frames of a speaking person. The proposed CNN generates sound features for each frame based on its neighboring frames. Waveforms are then synthesized from the learned speech features to produce intelligible speech. We show that by leveraging the automatic feature learning capabilities of a CNN, we can obtain state-of-the-art word intelligibility on the GRID dataset,","authors_text":"Ariel Ephrat, Shmuel Peleg","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-02T19:00:22Z","title":"Vid2speech: Speech Reconstruction from Silent Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.00495","kind":"arxiv","version":2},"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:e50db9ed4f9454ee5c41db8adbc4ca03b59fe64c62d492070b68b089ef7f8f41","target":"record","created_at":"2026-05-18T00:53:11Z","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":"4c3536f1e0c2159dbc14502c7db5920ed6e9fcb354cb8bae18b9301e6c81c458","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-01-02T19:00:22Z","title_canon_sha256":"7ec4283314fddab4b94320735e891370758bb205a040e45ad3d7dca7ebc2df14"},"schema_version":"1.0","source":{"id":"1701.00495","kind":"arxiv","version":2}},"canonical_sha256":"cbb6d3b77a73dbc2995463639e6c3be0e0cb6dd4e50eaf244ed9699c7caaec88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbb6d3b77a73dbc2995463639e6c3be0e0cb6dd4e50eaf244ed9699c7caaec88","first_computed_at":"2026-05-18T00:53:11.865802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:11.865802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXve4fVb6zSNWqUNCWYhCpC8+1YFVx8GiQUqoX6lqrkV2isusGPZbfIFIrL43MsBj1kKy0BsLijVRoJevudDCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:11.866257Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.00495","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e50db9ed4f9454ee5c41db8adbc4ca03b59fe64c62d492070b68b089ef7f8f41","sha256:3d5f4aa24217e83b4e3b406f466ab47143881968cb34077700c8d88a53034636"],"state_sha256":"07dd55a44d30ab0a545f5768a0635b5013ad25638750c8029142d1d169014427"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+2HR3BdhQxdOpzwajS1ggXWCmN2l+K1H949uf1iriBoR91XCc6BfX9iOcdTTHE3flWGithYtttP0cGGTjYVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:02:14.373468Z","bundle_sha256":"fd8c94818a20950b9b25c6581c60a74965642d5498926e3294d233d2c1195a3b"}}