{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GQSNPUHPST53R6GTPIVLLXR5D7","short_pith_number":"pith:GQSNPUHP","canonical_record":{"source":{"id":"1903.10195","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-03-25T09:27:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"affeacee5882957720bc50c9ed25f2e8cfa84a84ec0a4cf3aeb44cbb91a9be33","abstract_canon_sha256":"e16f5ec63b43ba059ebc0714861a505b57ad8b66d9cb8eb71ca91636551149f7"},"schema_version":"1.0"},"canonical_sha256":"3424d7d0ef94fbb8f8d37a2ab5de3d1ff541d3389306b378122600b917619868","source":{"kind":"arxiv","id":"1903.10195","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10195","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10195v1","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10195","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"GQSNPUHPST53","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GQSNPUHPST53R6GT","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GQSNPUHP","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GQSNPUHPST53R6GTPIVLLXR5D7","target":"record","payload":{"canonical_record":{"source":{"id":"1903.10195","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-03-25T09:27:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"affeacee5882957720bc50c9ed25f2e8cfa84a84ec0a4cf3aeb44cbb91a9be33","abstract_canon_sha256":"e16f5ec63b43ba059ebc0714861a505b57ad8b66d9cb8eb71ca91636551149f7"},"schema_version":"1.0"},"canonical_sha256":"3424d7d0ef94fbb8f8d37a2ab5de3d1ff541d3389306b378122600b917619868","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:30.365438Z","signature_b64":"O8iXpJijgb6sX1LFJKyT0sUTmAkRNWj0BtB0ZcMm3657Qor2FvRkvhIONz1JTIxvAOM4Nhfks81J2imXVHnqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3424d7d0ef94fbb8f8d37a2ab5de3d1ff541d3389306b378122600b917619868","last_reissued_at":"2026-05-17T23:50:30.364864Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:30.364864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.10195","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":"2026-05-17T23:50:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lBSygnV1IepIU1IBdZ7cMfylk00+1s5IzS1aloIFKkx4PU1dju8z04IhKoQ4EfZFxa8VvNGVf1dJv6i7uTLrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T11:24:03.500153Z"},"content_sha256":"85e79c7eeba44b2063f9e875c02b7bcdd73b9dbff2970f12facc34ab4ddaad0a","schema_version":"1.0","event_id":"sha256:85e79c7eeba44b2063f9e875c02b7bcdd73b9dbff2970f12facc34ab4ddaad0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GQSNPUHPST53R6GTPIVLLXR5D7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Amaia Salvador, Amanda Duarte, Eva Mohedano, Francisco Roldan, Janna Escur, Jordi Torres, Kevin McGuinness, Miquel Tubau, Santiago Pascual, Xavier Giro-i-Nieto","submitted_at":"2019-03-25T09:27:44Z","abstract_excerpt":"Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face images of a speaker by conditioning a Generative Adversarial Network (GAN) with raw speech input. We propose a deep neural network that is trained from scratch in an end-to-end fashion, generating a face directly from the raw speech waveform without any additional identity information (e.g reference image or one-hot encoding). Our model is trained in a self-supervised approach by exploiting the audio and visual signal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10195","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":"2026-05-17T23:50:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3NSyqakrJ2TQs5cjIkeOCW4R/81iCTRe5IuLmmleScF49MTaJwXqnw39NvokFBBQxufd4clfTgDdLrrmk2dVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T11:24:03.500514Z"},"content_sha256":"98ea8aa155e17117d3ce573e8d4fa54f3163c1518d69cc0af62d69cccb327b57","schema_version":"1.0","event_id":"sha256:98ea8aa155e17117d3ce573e8d4fa54f3163c1518d69cc0af62d69cccb327b57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GQSNPUHPST53R6GTPIVLLXR5D7/bundle.json","state_url":"https://pith.science/pith/GQSNPUHPST53R6GTPIVLLXR5D7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GQSNPUHPST53R6GTPIVLLXR5D7/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":"2026-07-03T11:24:03Z","links":{"resolver":"https://pith.science/pith/GQSNPUHPST53R6GTPIVLLXR5D7","bundle":"https://pith.science/pith/GQSNPUHPST53R6GTPIVLLXR5D7/bundle.json","state":"https://pith.science/pith/GQSNPUHPST53R6GTPIVLLXR5D7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GQSNPUHPST53R6GTPIVLLXR5D7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GQSNPUHPST53R6GTPIVLLXR5D7","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":"e16f5ec63b43ba059ebc0714861a505b57ad8b66d9cb8eb71ca91636551149f7","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-03-25T09:27:44Z","title_canon_sha256":"affeacee5882957720bc50c9ed25f2e8cfa84a84ec0a4cf3aeb44cbb91a9be33"},"schema_version":"1.0","source":{"id":"1903.10195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.10195","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"arxiv_version","alias_value":"1903.10195v1","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10195","created_at":"2026-05-17T23:50:30Z"},{"alias_kind":"pith_short_12","alias_value":"GQSNPUHPST53","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GQSNPUHPST53R6GT","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GQSNPUHP","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:98ea8aa155e17117d3ce573e8d4fa54f3163c1518d69cc0af62d69cccb327b57","target":"graph","created_at":"2026-05-17T23:50:30Z","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 is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face images of a speaker by conditioning a Generative Adversarial Network (GAN) with raw speech input. We propose a deep neural network that is trained from scratch in an end-to-end fashion, generating a face directly from the raw speech waveform without any additional identity information (e.g reference image or one-hot encoding). Our model is trained in a self-supervised approach by exploiting the audio and visual signal","authors_text":"Amaia Salvador, Amanda Duarte, Eva Mohedano, Francisco Roldan, Janna Escur, Jordi Torres, Kevin McGuinness, Miquel Tubau, Santiago Pascual, Xavier Giro-i-Nieto","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-03-25T09:27:44Z","title":"Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10195","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":"sha256:85e79c7eeba44b2063f9e875c02b7bcdd73b9dbff2970f12facc34ab4ddaad0a","target":"record","created_at":"2026-05-17T23:50:30Z","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":"e16f5ec63b43ba059ebc0714861a505b57ad8b66d9cb8eb71ca91636551149f7","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2019-03-25T09:27:44Z","title_canon_sha256":"affeacee5882957720bc50c9ed25f2e8cfa84a84ec0a4cf3aeb44cbb91a9be33"},"schema_version":"1.0","source":{"id":"1903.10195","kind":"arxiv","version":1}},"canonical_sha256":"3424d7d0ef94fbb8f8d37a2ab5de3d1ff541d3389306b378122600b917619868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3424d7d0ef94fbb8f8d37a2ab5de3d1ff541d3389306b378122600b917619868","first_computed_at":"2026-05-17T23:50:30.364864Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:30.364864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O8iXpJijgb6sX1LFJKyT0sUTmAkRNWj0BtB0ZcMm3657Qor2FvRkvhIONz1JTIxvAOM4Nhfks81J2imXVHnqBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:30.365438Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.10195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85e79c7eeba44b2063f9e875c02b7bcdd73b9dbff2970f12facc34ab4ddaad0a","sha256:98ea8aa155e17117d3ce573e8d4fa54f3163c1518d69cc0af62d69cccb327b57"],"state_sha256":"ccd87b4c8743eca4ba4409e8ce5144c90aa07e954f43580bfad108a35c1e9e00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OXB4Ew1ubqAxgv56dVdh9kHzG3JmeOT2h5X4RBiM7kr/u/i0FCUkEyaSPEU+6QhDM5WEE5x/i59u0IYhIpGLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T11:24:03.502479Z","bundle_sha256":"737eb9c27aaf636ccbfadfc816b37ee500956c4438ebbfacb5465c4cc562a905"}}