{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IXRYPLR24OQHWHTNRO2N4TDKLS","short_pith_number":"pith:IXRYPLR2","schema_version":"1.0","canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","source":{"kind":"arxiv","id":"2501.03181","version":2},"attestation_state":"computed","paper":{"title":"FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiawei Zhang, Jun Wang, Tian-Hao Zhang, Xinyuan Qian, Xu-Cheng Yin","submitted_at":"2025-01-02T02:00:15Z","abstract_excerpt":"Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces, thereby restricting effective speech synthesis from applying to vast potential usage scenarios with diverse characters and image styles. To solve this issue, we introduce a novel FaceSpeak approach. It extracts salient identity characteristics and emotional representations from a wide variety of image styles. Meanwhile, it mi"},"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":"2501.03181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T02:00:15Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"79319c6c7e6129d2d3a97868e67e68d7743a7c5fc15cb0b525c3804da663dc4c","abstract_canon_sha256":"3518a348f46cb5e13c7cddd870e3d9e68060a6a30eb517418b0e2a82140c73ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:35.150185Z","signature_b64":"JuCr6fn1iNNxJgBtbKVzI3JhY5vcEVfhw7pJGC0zplvxh441DmV9xqFX7ckrFrlIGctNWgXD6Cu6tAFO71eBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","last_reissued_at":"2026-07-05T10:49:35.149761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:35.149761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiawei Zhang, Jun Wang, Tian-Hao Zhang, Xinyuan Qian, Xu-Cheng Yin","submitted_at":"2025-01-02T02:00:15Z","abstract_excerpt":"Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces, thereby restricting effective speech synthesis from applying to vast potential usage scenarios with diverse characters and image styles. To solve this issue, we introduce a novel FaceSpeak approach. It extracts salient identity characteristics and emotional representations from a wide variety of image styles. Meanwhile, it mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03181","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/2501.03181/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.03181","created_at":"2026-07-05T10:49:35.149819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03181v2","created_at":"2026-07-05T10:49:35.149819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03181","created_at":"2026-07-05T10:49:35.149819+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXRYPLR24OQH","created_at":"2026-07-05T10:49:35.149819+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXRYPLR24OQHWHTN","created_at":"2026-07-05T10:49:35.149819+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXRYPLR2","created_at":"2026-07-05T10:49:35.149819+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/IXRYPLR24OQHWHTNRO2N4TDKLS","json":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS.json","graph_json":"https://pith.science/api/pith-number/IXRYPLR24OQHWHTNRO2N4TDKLS/graph.json","events_json":"https://pith.science/api/pith-number/IXRYPLR24OQHWHTNRO2N4TDKLS/events.json","paper":"https://pith.science/paper/IXRYPLR2"},"agent_actions":{"view_html":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS","download_json":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS.json","view_paper":"https://pith.science/paper/IXRYPLR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03181&json=true","fetch_graph":"https://pith.science/api/pith-number/IXRYPLR24OQHWHTNRO2N4TDKLS/graph.json","fetch_events":"https://pith.science/api/pith-number/IXRYPLR24OQHWHTNRO2N4TDKLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/action/storage_attestation","attest_author":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/action/author_attestation","sign_citation":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/action/citation_signature","submit_replication":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/action/replication_record"}},"created_at":"2026-07-05T10:49:35.149819+00:00","updated_at":"2026-07-05T10:49:35.149819+00:00"}