{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WCXAII6OA22ENWZZYKLZQSGIA4","short_pith_number":"pith:WCXAII6O","canonical_record":{"source":{"id":"1905.06860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-15T00:23:58Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"5dcab749e976e04245105b6f1331a64e6ff8bce2c515c51d442c5bdf60820041","abstract_canon_sha256":"78ede7ee5e52794b9ccbad20b4cda3cbd8d425f22314667e67d45c376ea4eb02"},"schema_version":"1.0"},"canonical_sha256":"b0ae0423ce06b446db39c2979848c807162cb166747884955ffb7c9afa4f2f7f","source":{"kind":"arxiv","id":"1905.06860","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06860","created_at":"2026-05-17T23:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06860v1","created_at":"2026-05-17T23:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06860","created_at":"2026-05-17T23:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"WCXAII6OA22E","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WCXAII6OA22ENWZZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WCXAII6O","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WCXAII6OA22ENWZZYKLZQSGIA4","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06860","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-15T00:23:58Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"5dcab749e976e04245105b6f1331a64e6ff8bce2c515c51d442c5bdf60820041","abstract_canon_sha256":"78ede7ee5e52794b9ccbad20b4cda3cbd8d425f22314667e67d45c376ea4eb02"},"schema_version":"1.0"},"canonical_sha256":"b0ae0423ce06b446db39c2979848c807162cb166747884955ffb7c9afa4f2f7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:00.811275Z","signature_b64":"Vj1e84ys5EmieRf3w6nUdR/YkJdcf0I1osOaMtMt5gQyK4znqR/RKGL2CvGxN7FhXZnIHyAFqYnuLpqWAmMyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0ae0423ce06b446db39c2979848c807162cb166747884955ffb7c9afa4f2f7f","last_reissued_at":"2026-05-17T23:46:00.810636Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:00.810636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06860","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":"2026-05-17T23:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxU79NLeUfGjWaAzgk+il3zEAqp5Duh1LIFIRbBxBr+9Yg/a+JpPAk8yqtaFDiviCOIHdY2J8jrQGQo2/nk/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:39:15.380089Z"},"content_sha256":"0c8479bb40658943035b969b18f1df4b59a21bddefc9aa7490ca2a3c58d56921","schema_version":"1.0","event_id":"sha256:0c8479bb40658943035b969b18f1df4b59a21bddefc9aa7490ca2a3c58d56921"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WCXAII6OA22ENWZZYKLZQSGIA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Gabriele Fanelli, Justin Binder, Nicholas Apostoloff, Paul Dixon, Sachin Kajareker, Thibaut Weise","submitted_at":"2019-05-15T00:23:58Z","abstract_excerpt":"Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, and depth data required to reliably train the DNNs, especially for speaker-independent models. In this paper, we investigate adapting an automatic speech recognition (ASR) acoustic model (AM) for the visual speech synthesis problem. We train the AM on ten thousand hours of audio-on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06860","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":""},"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":"2026-05-17T23:46:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mO2jT7iyg6BEjKNiSCr7KmMh1FA4IznEcHfkuO7D6k5FbuEB7zWHiHcKCJxrVwTwHjZ1hyIlAoAvcVdjlt19AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T16:39:15.380461Z"},"content_sha256":"65f3b733fa5b0de7bfc7401c46f592892a1305c7edd0284d6e7d063da47a1f44","schema_version":"1.0","event_id":"sha256:65f3b733fa5b0de7bfc7401c46f592892a1305c7edd0284d6e7d063da47a1f44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCXAII6OA22ENWZZYKLZQSGIA4/bundle.json","state_url":"https://pith.science/pith/WCXAII6OA22ENWZZYKLZQSGIA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCXAII6OA22ENWZZYKLZQSGIA4/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":"2026-06-30T16:39:15Z","links":{"resolver":"https://pith.science/pith/WCXAII6OA22ENWZZYKLZQSGIA4","bundle":"https://pith.science/pith/WCXAII6OA22ENWZZYKLZQSGIA4/bundle.json","state":"https://pith.science/pith/WCXAII6OA22ENWZZYKLZQSGIA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCXAII6OA22ENWZZYKLZQSGIA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WCXAII6OA22ENWZZYKLZQSGIA4","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":"78ede7ee5e52794b9ccbad20b4cda3cbd8d425f22314667e67d45c376ea4eb02","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-15T00:23:58Z","title_canon_sha256":"5dcab749e976e04245105b6f1331a64e6ff8bce2c515c51d442c5bdf60820041"},"schema_version":"1.0","source":{"id":"1905.06860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06860","created_at":"2026-05-17T23:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06860v1","created_at":"2026-05-17T23:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06860","created_at":"2026-05-17T23:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"WCXAII6OA22E","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"WCXAII6OA22ENWZZ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"WCXAII6O","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:65f3b733fa5b0de7bfc7401c46f592892a1305c7edd0284d6e7d063da47a1f44","target":"graph","created_at":"2026-05-17T23:46:00Z","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":"Speech-driven visual speech synthesis involves mapping features extracted from acoustic speech to the corresponding lip animation controls for a face model. This mapping can take many forms, but a powerful approach is to use deep neural networks (DNNs). However, a limitation is the lack of synchronized audio, video, and depth data required to reliably train the DNNs, especially for speaker-independent models. In this paper, we investigate adapting an automatic speech recognition (ASR) acoustic model (AM) for the visual speech synthesis problem. We train the AM on ten thousand hours of audio-on","authors_text":"Ahmed Hussen Abdelaziz, Barry-John Theobald, Gabriele Fanelli, Justin Binder, Nicholas Apostoloff, Paul Dixon, Sachin Kajareker, Thibaut Weise","cross_cats":["cs.LG","cs.SD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-15T00:23:58Z","title":"Speaker-Independent Speech-Driven Visual Speech Synthesis using Domain-Adapted Acoustic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06860","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":"sha256:0c8479bb40658943035b969b18f1df4b59a21bddefc9aa7490ca2a3c58d56921","target":"record","created_at":"2026-05-17T23:46:00Z","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":"78ede7ee5e52794b9ccbad20b4cda3cbd8d425f22314667e67d45c376ea4eb02","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-05-15T00:23:58Z","title_canon_sha256":"5dcab749e976e04245105b6f1331a64e6ff8bce2c515c51d442c5bdf60820041"},"schema_version":"1.0","source":{"id":"1905.06860","kind":"arxiv","version":1}},"canonical_sha256":"b0ae0423ce06b446db39c2979848c807162cb166747884955ffb7c9afa4f2f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0ae0423ce06b446db39c2979848c807162cb166747884955ffb7c9afa4f2f7f","first_computed_at":"2026-05-17T23:46:00.810636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:00.810636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vj1e84ys5EmieRf3w6nUdR/YkJdcf0I1osOaMtMt5gQyK4znqR/RKGL2CvGxN7FhXZnIHyAFqYnuLpqWAmMyCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:00.811275Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c8479bb40658943035b969b18f1df4b59a21bddefc9aa7490ca2a3c58d56921","sha256:65f3b733fa5b0de7bfc7401c46f592892a1305c7edd0284d6e7d063da47a1f44"],"state_sha256":"dae8d763be1bed5e350572ec7333b7cbcfed87306a2fada2533bc09b53a899ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x+OQsI5rWc1YiOiDV+u0CE/HWbddXNVIFJezhtYvvFc11290nSNHYoZmNp3tSme6iwjGytsf2NB+7rgg8mxjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T16:39:15.382561Z","bundle_sha256":"9c21d2deabe9c9a2e9b522fd6cbc2295897191898748318aa044ac791d220aab"}}