{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RVJU2COF3XN7LQCZLLV7UV5UFL","short_pith_number":"pith:RVJU2COF","schema_version":"1.0","canonical_sha256":"8d534d09c5dddbf5c0595aebfa57b42ac8860023bc4c2663c980f3ed9158d1c9","source":{"kind":"arxiv","id":"1904.04540","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.04540","created_at":"2026-05-17T23:48:58.792943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04540v1","created_at":"2026-05-17T23:48:58.792943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04540","created_at":"2026-05-17T23:48:58.792943+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVJU2COF3XN7","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVJU2COF3XN7LQCZ","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVJU2COF","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL","json":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL.json","graph_json":"https://pith.science/api/pith-number/RVJU2COF3XN7LQCZLLV7UV5UFL/graph.json","events_json":"https://pith.science/api/pith-number/RVJU2COF3XN7LQCZLLV7UV5UFL/events.json","paper":"https://pith.science/paper/RVJU2COF"},"agent_actions":{"view_html":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL","download_json":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL.json","view_paper":"https://pith.science/paper/RVJU2COF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04540&json=true","fetch_graph":"https://pith.science/api/pith-number/RVJU2COF3XN7LQCZLLV7UV5UFL/graph.json","fetch_events":"https://pith.science/api/pith-number/RVJU2COF3XN7LQCZLLV7UV5UFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/action/storage_attestation","attest_author":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/action/author_attestation","sign_citation":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/action/citation_signature","submit_replication":"https://pith.science/pith/RVJU2COF3XN7LQCZLLV7UV5UFL/action/replication_record"}},"created_at":"2026-05-17T23:48:58.792943+00:00","updated_at":"2026-05-17T23:48:58.792943+00:00"}