{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MIMZFR6XVUULBR7KKLT4N3YFBQ","short_pith_number":"pith:MIMZFR6X","canonical_record":{"source":{"id":"2311.05844","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T13:46:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"f415af48dbe8c59be5162df639b84a9d464910a4da337e8f26e1abf6aaf784d8","abstract_canon_sha256":"f101da650766b106e27e7b74dfc7c54456b40792e09f030d0bb8eed5c7ab121a"},"schema_version":"1.0"},"canonical_sha256":"621992c7d7ad28b0c7ea52e7c6ef050c25b902daf4076b407921544b66c693a8","source":{"kind":"arxiv","id":"2311.05844","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05844","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05844v2","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05844","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"pith_short_12","alias_value":"MIMZFR6XVUUL","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"pith_short_16","alias_value":"MIMZFR6XVUULBR7K","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"pith_short_8","alias_value":"MIMZFR6X","created_at":"2026-07-05T09:54:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MIMZFR6XVUULBR7KKLT4N3YFBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05844","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T13:46:00Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"f415af48dbe8c59be5162df639b84a9d464910a4da337e8f26e1abf6aaf784d8","abstract_canon_sha256":"f101da650766b106e27e7b74dfc7c54456b40792e09f030d0bb8eed5c7ab121a"},"schema_version":"1.0"},"canonical_sha256":"621992c7d7ad28b0c7ea52e7c6ef050c25b902daf4076b407921544b66c693a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:43.335579Z","signature_b64":"AwTO9/vTDjOS1bNOYnUCIdMxygaqjviTTxyVFK+bAjoWHeuuwJFJOdPSIa1XYf72j7Nm63xZAOodNYNwKfljAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"621992c7d7ad28b0c7ea52e7c6ef050c25b902daf4076b407921544b66c693a8","last_reissued_at":"2026-07-05T09:54:43.335080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:43.335080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05844","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qu8/DeBZbi3ckaHJ+rwOpWtColfMjK6YSaSv+GT7IYAIxJ1b//M1t2QaUBxk73rGqbu9fMnPVCrntLzmLWUGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:37:12.751270Z"},"content_sha256":"1c019a7ddee7cbf11a44f225d45b2c65882e025c68235c73edf45ffb82d5e7d8","schema_version":"1.0","event_id":"sha256:1c019a7ddee7cbf11a44f225d45b2c65882e025c68235c73edf45ffb82d5e7d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MIMZFR6XVUULBR7KKLT4N3YFBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Eunho Yang, Minki Kang, Wooseok Han","submitted_at":"2023-09-25T13:46:00Z","abstract_excerpt":"Generating speech from a face image is crucial for developing virtual humans capable of interacting using their unique voices, without relying on pre-recorded human speech. In this paper, we propose Face-StyleSpeech, a zero-shot Text-To-Speech (TTS) synthesis model that generates natural speech conditioned on a face image rather than reference speech. We hypothesize that learning entire prosodic features from a face image poses a significant challenge. To address this, our TTS model incorporates both face and prosody encoders. The prosody encoder is specifically designed to model speech style "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05844","kind":"arxiv","version":2},"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/2311.05844/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":"2026-07-05T09:54:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"if0vpIxo20JV82JmQKj7iqg83b/xeC0yL2zQ4JaBqzPNtEDmTsQbycx14KjyIkbyKMj2bzgGjdIKe2h8URhrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:37:12.751848Z"},"content_sha256":"b2cabcaff02b8f9b93cb3c2cf8741cace2597aa2170cbfea2cc264d181e2d047","schema_version":"1.0","event_id":"sha256:b2cabcaff02b8f9b93cb3c2cf8741cace2597aa2170cbfea2cc264d181e2d047"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ/bundle.json","state_url":"https://pith.science/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ/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":"2026-08-10T12:37:12Z","links":{"resolver":"https://pith.science/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ","bundle":"https://pith.science/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ/bundle.json","state":"https://pith.science/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIMZFR6XVUULBR7KKLT4N3YFBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MIMZFR6XVUULBR7KKLT4N3YFBQ","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":"f101da650766b106e27e7b74dfc7c54456b40792e09f030d0bb8eed5c7ab121a","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T13:46:00Z","title_canon_sha256":"f415af48dbe8c59be5162df639b84a9d464910a4da337e8f26e1abf6aaf784d8"},"schema_version":"1.0","source":{"id":"2311.05844","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05844","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05844v2","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05844","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"pith_short_12","alias_value":"MIMZFR6XVUUL","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"pith_short_16","alias_value":"MIMZFR6XVUULBR7K","created_at":"2026-07-05T09:54:43Z"},{"alias_kind":"pith_short_8","alias_value":"MIMZFR6X","created_at":"2026-07-05T09:54:43Z"}],"graph_snapshots":[{"event_id":"sha256:b2cabcaff02b8f9b93cb3c2cf8741cace2597aa2170cbfea2cc264d181e2d047","target":"graph","created_at":"2026-07-05T09:54:43Z","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/2311.05844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating speech from a face image is crucial for developing virtual humans capable of interacting using their unique voices, without relying on pre-recorded human speech. In this paper, we propose Face-StyleSpeech, a zero-shot Text-To-Speech (TTS) synthesis model that generates natural speech conditioned on a face image rather than reference speech. We hypothesize that learning entire prosodic features from a face image poses a significant challenge. To address this, our TTS model incorporates both face and prosody encoders. The prosody encoder is specifically designed to model speech style ","authors_text":"Eunho Yang, Minki Kang, Wooseok Han","cross_cats":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T13:46:00Z","title":"Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05844","kind":"arxiv","version":2},"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":"sha256:1c019a7ddee7cbf11a44f225d45b2c65882e025c68235c73edf45ffb82d5e7d8","target":"record","created_at":"2026-07-05T09:54:43Z","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":"f101da650766b106e27e7b74dfc7c54456b40792e09f030d0bb8eed5c7ab121a","cross_cats_sorted":["cs.AI","cs.CL","cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-25T13:46:00Z","title_canon_sha256":"f415af48dbe8c59be5162df639b84a9d464910a4da337e8f26e1abf6aaf784d8"},"schema_version":"1.0","source":{"id":"2311.05844","kind":"arxiv","version":2}},"canonical_sha256":"621992c7d7ad28b0c7ea52e7c6ef050c25b902daf4076b407921544b66c693a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"621992c7d7ad28b0c7ea52e7c6ef050c25b902daf4076b407921544b66c693a8","first_computed_at":"2026-07-05T09:54:43.335080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:43.335080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AwTO9/vTDjOS1bNOYnUCIdMxygaqjviTTxyVFK+bAjoWHeuuwJFJOdPSIa1XYf72j7Nm63xZAOodNYNwKfljAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:43.335579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05844","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c019a7ddee7cbf11a44f225d45b2c65882e025c68235c73edf45ffb82d5e7d8","sha256:b2cabcaff02b8f9b93cb3c2cf8741cace2597aa2170cbfea2cc264d181e2d047"],"state_sha256":"3fddefdb4e56edf0876ab0ab0d3005d1e0ca7bb484a967e6da0222ae926ee355"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3z+zDzSPU1iotSp8p4W5wTC/hp2LbpfgVJbCFIL5KfyMYOhnxPMiiWH658I7++WoDyWKQtKd14Mtiv8bFlbAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:37:12.756067Z","bundle_sha256":"554a6e7a0762839e2d9876a29b315f2eb2938d88f61ea2e1624b602a49fe16f9"}}