{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2VAJBODQKOQZKELRH46EVIFYC","short_pith_number":"pith:K2VAJBOD","schema_version":"1.0","canonical_sha256":"56aa0485c3829d0ca88b89f9e25505c0b1e0c1776b838a0f3d20bca0c880ba42","source":{"kind":"arxiv","id":"2505.13082","version":1},"attestation_state":"computed","paper":{"title":"MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kyeongman Park, Kyomin Jung, Seongho Joo","submitted_at":"2025-05-19T13:13:46Z","abstract_excerpt":"We introduce MultiActor-Audiobook, a zero-shot approach for generating audiobooks that automatically produces consistent, expressive, and speaker-appropriate prosody, including intonation and emotion. Previous audiobook systems have several limitations: they require users to manually configure the speaker's prosody, read each sentence with a monotonic tone compared to voice actors, or rely on costly training. However, our MultiActor-Audiobook addresses these issues by introducing two novel processes: (1) MSP (**Multimodal Speaker Persona Generation**) and (2) LSI (**LLM-based Script Instructio"},"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":"2505.13082","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-19T13:13:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"284d88f9dbfa4b383572c7d2c9602a6842120ccb114b92a096485677ef3d2c89","abstract_canon_sha256":"6ec1dfb4a6666b10db1f31b644dc490012fb8c54f84d39949a4abba3aef04e64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:14.707577Z","signature_b64":"ud9sHbjo28j7vNmcaM3duhMF9BJKj3qeK4I3WvImBodAtROAb4jFO1RW3HoHJwPOk6sS2Jgv/Kz6RC85f6rACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56aa0485c3829d0ca88b89f9e25505c0b1e0c1776b838a0f3d20bca0c880ba42","last_reissued_at":"2026-07-05T11:05:14.707087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:14.707087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kyeongman Park, Kyomin Jung, Seongho Joo","submitted_at":"2025-05-19T13:13:46Z","abstract_excerpt":"We introduce MultiActor-Audiobook, a zero-shot approach for generating audiobooks that automatically produces consistent, expressive, and speaker-appropriate prosody, including intonation and emotion. Previous audiobook systems have several limitations: they require users to manually configure the speaker's prosody, read each sentence with a monotonic tone compared to voice actors, or rely on costly training. However, our MultiActor-Audiobook addresses these issues by introducing two novel processes: (1) MSP (**Multimodal Speaker Persona Generation**) and (2) LSI (**LLM-based Script Instructio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13082","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.13082/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":"2505.13082","created_at":"2026-07-05T11:05:14.707143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13082v1","created_at":"2026-07-05T11:05:14.707143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13082","created_at":"2026-07-05T11:05:14.707143+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2VAJBODQKOQ","created_at":"2026-07-05T11:05:14.707143+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2VAJBODQKOQZKEL","created_at":"2026-07-05T11:05:14.707143+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2VAJBOD","created_at":"2026-07-05T11:05:14.707143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09413","citing_title":"Evaluating the Expressive Appropriateness of Speech in Rich Contexts","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC","json":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC.json","graph_json":"https://pith.science/api/pith-number/K2VAJBODQKOQZKELRH46EVIFYC/graph.json","events_json":"https://pith.science/api/pith-number/K2VAJBODQKOQZKELRH46EVIFYC/events.json","paper":"https://pith.science/paper/K2VAJBOD"},"agent_actions":{"view_html":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC","download_json":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC.json","view_paper":"https://pith.science/paper/K2VAJBOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13082&json=true","fetch_graph":"https://pith.science/api/pith-number/K2VAJBODQKOQZKELRH46EVIFYC/graph.json","fetch_events":"https://pith.science/api/pith-number/K2VAJBODQKOQZKELRH46EVIFYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC/action/storage_attestation","attest_author":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC/action/author_attestation","sign_citation":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC/action/citation_signature","submit_replication":"https://pith.science/pith/K2VAJBODQKOQZKELRH46EVIFYC/action/replication_record"}},"created_at":"2026-07-05T11:05:14.707143+00:00","updated_at":"2026-07-05T11:05:14.707143+00:00"}