{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RVJU2COF3XN7LQCZLLV7UV5UFL","short_pith_number":"pith:RVJU2COF","canonical_record":{"source":{"id":"1904.04540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-09T08:53:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1dc13b9ed7193197f6e66267a8cf0b3b21af7c73adafefdfee91b782d72f06cc","abstract_canon_sha256":"6a3167c199f977babaa904daa6828ba03d1d403dfb3693a11f33cefe349af271"},"schema_version":"1.0"},"canonical_sha256":"8d534d09c5dddbf5c0595aebfa57b42ac8860023bc4c2663c980f3ed9158d1c9","source":{"kind":"arxiv","id":"1904.04540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04540","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04540v1","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04540","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"RVJU2COF3XN7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RVJU2COF3XN7LQCZ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RVJU2COF","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RVJU2COF3XN7LQCZLLV7UV5UFL","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-09T08:53:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1dc13b9ed7193197f6e66267a8cf0b3b21af7c73adafefdfee91b782d72f06cc","abstract_canon_sha256":"6a3167c199f977babaa904daa6828ba03d1d403dfb3693a11f33cefe349af271"},"schema_version":"1.0"},"canonical_sha256":"8d534d09c5dddbf5c0595aebfa57b42ac8860023bc4c2663c980f3ed9158d1c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:58.793250Z","signature_b64":"7oQYRCp7PHYtfGv+P927af4/IFO9fXwUYbAYWCW87mKcKu+uGs/D2wu9LieV8qz9dEDBFz14cxO0aCx6USZqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d534d09c5dddbf5c0595aebfa57b42ac8860023bc4c2663c980f3ed9158d1c9","last_reissued_at":"2026-05-17T23:48:58.792878Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:58.792878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04540","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":"2026-05-17T23:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pethObDss4NHTM4jbBFYhHa0a5PjbVkpBlDnFTRX+enIC64M5i7Lvg/nyQ1zuyu/TmE0UrAnkDbyGytUWvlQCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:57:22.066720Z"},"content_sha256":"16947c02cd82b0739da6443c37e9b1e5003a2b7652469215efdac1452cb2d90b","schema_version":"1.0","event_id":"sha256:16947c02cd82b0739da6443c37e9b1e5003a2b7652469215efdac1452cb2d90b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RVJU2COF3XN7LQCZLLV7UV5UFL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Crossmodal Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.SD","authors_text":"Aaron Valero Puche, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Yasunori Ohishi","submitted_at":"2019-04-09T08:53:10Z","abstract_excerpt":"Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the input speech by leveraging the correlation between faces and voices. We propose a model, consisting of a speech converter, a face encoder/decoder and a voice encoder. We use the latent code of an input face image encoded by the face encoder as the auxiliary input into the speech conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04540","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":"2026-05-17T23:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pEeskG5gZ6ObmY3aOa49P5mlG0pvCzAMllY/ZMRBRuOC/GgQBoCVMLP2yyuTiRhA1mgAXP0f4sMZtGP1VeCgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:57:22.067063Z"},"content_sha256":"cfca3759b6f647fdd49fa4d37f6642967b27e1e4815a24fe4544012c8455e32d","schema_version":"1.0","event_id":"sha256:cfca3759b6f647fdd49fa4d37f6642967b27e1e4815a24fe4544012c8455e32d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/bundle.json","state_url":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/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":"2026-06-02T02:57:22Z","links":{"resolver":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL","bundle":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/bundle.json","state":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RVJU2COF3XN7LQCZLLV7UV5UFL","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":"6a3167c199f977babaa904daa6828ba03d1d403dfb3693a11f33cefe349af271","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-09T08:53:10Z","title_canon_sha256":"1dc13b9ed7193197f6e66267a8cf0b3b21af7c73adafefdfee91b782d72f06cc"},"schema_version":"1.0","source":{"id":"1904.04540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04540","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04540v1","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04540","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"RVJU2COF3XN7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"RVJU2COF3XN7LQCZ","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"RVJU2COF","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:cfca3759b6f647fdd49fa4d37f6642967b27e1e4815a24fe4544012c8455e32d","target":"graph","created_at":"2026-05-17T23:48:58Z","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":"Humans are able to imagine a person's voice from the person's appearance and imagine the person's appearance from his/her voice. In this paper, we make the first attempt to develop a method that can convert speech into a voice that matches an input face image and generate a face image that matches the voice of the input speech by leveraging the correlation between faces and voices. We propose a model, consisting of a speech converter, a face encoder/decoder and a voice encoder. We use the latent code of an input face image encoded by the face encoder as the auxiliary input into the speech conv","authors_text":"Aaron Valero Puche, Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Yasunori Ohishi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-09T08:53:10Z","title":"Crossmodal Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04540","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":"sha256:16947c02cd82b0739da6443c37e9b1e5003a2b7652469215efdac1452cb2d90b","target":"record","created_at":"2026-05-17T23:48:58Z","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":"6a3167c199f977babaa904daa6828ba03d1d403dfb3693a11f33cefe349af271","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-04-09T08:53:10Z","title_canon_sha256":"1dc13b9ed7193197f6e66267a8cf0b3b21af7c73adafefdfee91b782d72f06cc"},"schema_version":"1.0","source":{"id":"1904.04540","kind":"arxiv","version":1}},"canonical_sha256":"8d534d09c5dddbf5c0595aebfa57b42ac8860023bc4c2663c980f3ed9158d1c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d534d09c5dddbf5c0595aebfa57b42ac8860023bc4c2663c980f3ed9158d1c9","first_computed_at":"2026-05-17T23:48:58.792878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:58.792878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7oQYRCp7PHYtfGv+P927af4/IFO9fXwUYbAYWCW87mKcKu+uGs/D2wu9LieV8qz9dEDBFz14cxO0aCx6USZqAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:58.793250Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16947c02cd82b0739da6443c37e9b1e5003a2b7652469215efdac1452cb2d90b","sha256:cfca3759b6f647fdd49fa4d37f6642967b27e1e4815a24fe4544012c8455e32d"],"state_sha256":"5718a4045cd2016352a8617589d01834405745f717b40d85037054cdf8f49700"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"30zyv+nhqd9gQBcXj5Jmz4gtP0Sx2L9y7J1p+F750N1nwxGIMzhpU49onDhVaricpqHnULwb/mDoSjazKk8WCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T02:57:22.068958Z","bundle_sha256":"1c560093a3cb968d79d08cf16dd60bced3fe896ac7d692140dc8ca2f18259986"}}