{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VDH6SHJVEWLG7FXYPH5JY6MARZ","short_pith_number":"pith:VDH6SHJV","canonical_record":{"source":{"id":"2111.12890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T03:35:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5aa775bf9412a2222e49a89324cd2d6e7e0b77bf24361f767eb6d699a8855a3e","abstract_canon_sha256":"15294c1770a58ea3de8b71bdc90de96aca41f66fbcb6a2b56b7eafce5ab31eb2"},"schema_version":"1.0"},"canonical_sha256":"a8cfe91d3525966f96f879fa9c79808e45fc8b423e773de4c788604f45e4e85c","source":{"kind":"arxiv","id":"2111.12890","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12890","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12890v1","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12890","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"VDH6SHJVEWLG","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"VDH6SHJVEWLG7FXY","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"VDH6SHJV","created_at":"2026-07-05T03:34:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VDH6SHJVEWLG7FXYPH5JY6MARZ","target":"record","payload":{"canonical_record":{"source":{"id":"2111.12890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T03:35:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5aa775bf9412a2222e49a89324cd2d6e7e0b77bf24361f767eb6d699a8855a3e","abstract_canon_sha256":"15294c1770a58ea3de8b71bdc90de96aca41f66fbcb6a2b56b7eafce5ab31eb2"},"schema_version":"1.0"},"canonical_sha256":"a8cfe91d3525966f96f879fa9c79808e45fc8b423e773de4c788604f45e4e85c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:59.749479Z","signature_b64":"7vqSFqxuaCcEFd+QluELfK70ppYwAXYMPP8u6LNj6Fv0bBPbDHnpsZzWGuuWClwu8l3ftrL2mYUZkaC/Y3ypCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8cfe91d3525966f96f879fa9c79808e45fc8b423e773de4c788604f45e4e85c","last_reissued_at":"2026-07-05T03:34:59.749030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:59.749030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.12890","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":"2026-07-05T03:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lfWMRigQy/SQtjSMj/z/FVosqfoaDdrNjAJa53vzbd3nkgrHiebqMLaXj0Yo3AajLRSFwwVnDAMkOXjWQeEJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:21:08.413243Z"},"content_sha256":"81b3a1468d112a884a14e8c23b70fbf9ad814f4511447f6730c7d10744e8632d","schema_version":"1.0","event_id":"sha256:81b3a1468d112a884a14e8c23b70fbf9ad814f4511447f6730c7d10744e8632d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VDH6SHJVEWLG7FXYPH5JY6MARZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V2C: Visual Voice Cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Jiaqiu Zhou, Mingkui Tan, Qi Chen, Qi Wu, Yuankai Qi, Yuanqing Li","submitted_at":"2021-11-25T03:35:18Z","abstract_excerpt":"Existing Voice Cloning (VC) tasks aim to convert a paragraph text to a speech with desired voice specified by a reference audio. This has significantly boosted the development of artificial speech applications. However, there also exist many scenarios that cannot be well reflected by these VC tasks, such as movie dubbing, which requires the speech to be with emotions consistent with the movie plots. To fill this gap, in this work we propose a new task named Visual Voice Cloning (V2C), which seeks to convert a paragraph of text to a speech with both desired voice specified by a reference audio "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12890","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/2111.12890/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":"2026-07-05T03:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gYxoJ6PsbghX5f53DZtWsz2EuffzBIFr1Ftg76FvPqZJOEKr4fgrKd3v8SWthiw375y4v8/JgG4Sk1PyIFiOBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:21:08.413813Z"},"content_sha256":"00bea0ae9439243426df545b1b3b426ce338168a8f6c20abb1ad0c1f190b23e7","schema_version":"1.0","event_id":"sha256:00bea0ae9439243426df545b1b3b426ce338168a8f6c20abb1ad0c1f190b23e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ/bundle.json","state_url":"https://pith.science/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ/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":"2026-08-09T02:21:08Z","links":{"resolver":"https://pith.science/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ","bundle":"https://pith.science/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ/bundle.json","state":"https://pith.science/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDH6SHJVEWLG7FXYPH5JY6MARZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VDH6SHJVEWLG7FXYPH5JY6MARZ","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":"15294c1770a58ea3de8b71bdc90de96aca41f66fbcb6a2b56b7eafce5ab31eb2","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T03:35:18Z","title_canon_sha256":"5aa775bf9412a2222e49a89324cd2d6e7e0b77bf24361f767eb6d699a8855a3e"},"schema_version":"1.0","source":{"id":"2111.12890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12890","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12890v1","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12890","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"VDH6SHJVEWLG","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"VDH6SHJVEWLG7FXY","created_at":"2026-07-05T03:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"VDH6SHJV","created_at":"2026-07-05T03:34:59Z"}],"graph_snapshots":[{"event_id":"sha256:00bea0ae9439243426df545b1b3b426ce338168a8f6c20abb1ad0c1f190b23e7","target":"graph","created_at":"2026-07-05T03:34:59Z","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/2111.12890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing Voice Cloning (VC) tasks aim to convert a paragraph text to a speech with desired voice specified by a reference audio. This has significantly boosted the development of artificial speech applications. However, there also exist many scenarios that cannot be well reflected by these VC tasks, such as movie dubbing, which requires the speech to be with emotions consistent with the movie plots. To fill this gap, in this work we propose a new task named Visual Voice Cloning (V2C), which seeks to convert a paragraph of text to a speech with both desired voice specified by a reference audio ","authors_text":"Jiaqiu Zhou, Mingkui Tan, Qi Chen, Qi Wu, Yuankai Qi, Yuanqing Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T03:35:18Z","title":"V2C: Visual Voice Cloning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12890","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":"sha256:81b3a1468d112a884a14e8c23b70fbf9ad814f4511447f6730c7d10744e8632d","target":"record","created_at":"2026-07-05T03:34:59Z","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":"15294c1770a58ea3de8b71bdc90de96aca41f66fbcb6a2b56b7eafce5ab31eb2","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T03:35:18Z","title_canon_sha256":"5aa775bf9412a2222e49a89324cd2d6e7e0b77bf24361f767eb6d699a8855a3e"},"schema_version":"1.0","source":{"id":"2111.12890","kind":"arxiv","version":1}},"canonical_sha256":"a8cfe91d3525966f96f879fa9c79808e45fc8b423e773de4c788604f45e4e85c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8cfe91d3525966f96f879fa9c79808e45fc8b423e773de4c788604f45e4e85c","first_computed_at":"2026-07-05T03:34:59.749030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:34:59.749030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vqSFqxuaCcEFd+QluELfK70ppYwAXYMPP8u6LNj6Fv0bBPbDHnpsZzWGuuWClwu8l3ftrL2mYUZkaC/Y3ypCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:34:59.749479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81b3a1468d112a884a14e8c23b70fbf9ad814f4511447f6730c7d10744e8632d","sha256:00bea0ae9439243426df545b1b3b426ce338168a8f6c20abb1ad0c1f190b23e7"],"state_sha256":"8181dc8f6590c06f2f27c274540b2a0d552352d0e09fe62764e6fde81f2ba317"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vxlubYeMhuhTLcgvoXc8Pmx3pUdLlwJ/BL38heGhKeJeyH6tNQv+qtX8UxA8+tH9oOgmWZtUalLY7yEStu5nCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:21:08.417744Z","bundle_sha256":"8025028c4e7e4d12921deb68ccec6e619bc05e87d04148a35fef668ae59a8f3b"}}