{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XUYPIL57P5CWLZ6Q6QOXNFWYLT","short_pith_number":"pith:XUYPIL57","schema_version":"1.0","canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","source":{"kind":"arxiv","id":"1905.09773","version":1},"attestation_state":"computed","paper":{"title":"Speech2Face: Learning the Face Behind a Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Changil Kim, Inbar Mosseri, Michael Rubinstein, Tae-Hyun Oh, Tali Dekel, William T. Freeman, Wojciech Matusik","submitted_at":"2019-05-23T16:54:17Z","abstract_excerpt":"How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of"},"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":"1905.09773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-23T16:54:17Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"7e333674281527b6c34b8e5c62b676388e114328244611da70aed20f765beb40","abstract_canon_sha256":"355d65523a239ecbbc00ec06fd7d74b6995e96838f17b000dd14266dbae67bbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:16.080270Z","signature_b64":"kV4o819VlbTWIjABkoPOPkMvXY8LiELjwdyztzl66a7jUBJ/XVhZpzM7/6Z0NjT860Z98LTvgxuMb77FpC/0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd30f42fbf7f4565e7d0f41d7696d85cd345a8d77bb8373f2de0a8c76c3b1b52","last_reissued_at":"2026-05-17T23:45:16.079677Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:16.079677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech2Face: Learning the Face Behind a Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Changil Kim, Inbar Mosseri, Michael Rubinstein, Tae-Hyun Oh, Tali Dekel, William T. Freeman, Wojciech Matusik","submitted_at":"2019-05-23T16:54:17Z","abstract_excerpt":"How much can we infer about a person's looks from the way they speak? In this paper, we study the task of reconstructing a facial image of a person from a short audio recording of that person speaking. We design and train a deep neural network to perform this task using millions of natural Internet/YouTube videos of people speaking. During training, our model learns voice-face correlations that allow it to produce images that capture various physical attributes of the speakers such as age, gender and ethnicity. This is done in a self-supervised manner, by utilizing the natural co-occurrence of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09773","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":"1905.09773","created_at":"2026-05-17T23:45:16.079762+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09773v1","created_at":"2026-05-17T23:45:16.079762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09773","created_at":"2026-05-17T23:45:16.079762+00:00"},{"alias_kind":"pith_short_12","alias_value":"XUYPIL57P5CW","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XUYPIL57P5CWLZ6Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XUYPIL57","created_at":"2026-05-18T12:33:33.725879+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/XUYPIL57P5CWLZ6Q6QOXNFWYLT","json":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT.json","graph_json":"https://pith.science/api/pith-number/XUYPIL57P5CWLZ6Q6QOXNFWYLT/graph.json","events_json":"https://pith.science/api/pith-number/XUYPIL57P5CWLZ6Q6QOXNFWYLT/events.json","paper":"https://pith.science/paper/XUYPIL57"},"agent_actions":{"view_html":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT","download_json":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT.json","view_paper":"https://pith.science/paper/XUYPIL57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09773&json=true","fetch_graph":"https://pith.science/api/pith-number/XUYPIL57P5CWLZ6Q6QOXNFWYLT/graph.json","fetch_events":"https://pith.science/api/pith-number/XUYPIL57P5CWLZ6Q6QOXNFWYLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/action/storage_attestation","attest_author":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/action/author_attestation","sign_citation":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/action/citation_signature","submit_replication":"https://pith.science/pith/XUYPIL57P5CWLZ6Q6QOXNFWYLT/action/replication_record"}},"created_at":"2026-05-17T23:45:16.079762+00:00","updated_at":"2026-05-17T23:45:16.079762+00:00"}