{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SNTVCG6IWNLKSXNINH2FT4D2GV","short_pith_number":"pith:SNTVCG6I","schema_version":"1.0","canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","source":{"kind":"arxiv","id":"2504.02386","version":1},"attestation_state":"computed","paper":{"title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"David Harwath, Jeongsoo Choi, Joon Son Chung, Kim Sung-Bin, Puyuan Peng, Tae-Hyun Oh","submitted_at":"2025-04-03T08:24:47Z","abstract_excerpt":"We present VoiceCraft-Dub, a novel approach for automated video dubbing that synthesizes high-quality speech from text and facial cues. This task has broad applications in filmmaking, multimedia creation, and assisting voice-impaired individuals. Building on the success of Neural Codec Language Models (NCLMs) for speech synthesis, our method extends their capabilities by incorporating video features, ensuring that synthesized speech is time-synchronized and expressively aligned with facial movements while preserving natural prosody. To inject visual cues, we design adapters to align facial fea"},"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":"2504.02386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T08:24:47Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"849f415debbbc5b8b265ce337cdbdae8ad796bbe1eeaa3cf6edf3de1079d589e","abstract_canon_sha256":"14ab27861f161e2b3d8222dac65dcc494e2b89145750ef692ab5e55748758bab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:56.117376Z","signature_b64":"4hmlE+TFzzfUvedr89zE84COXx6UGU5kny3OYbcTuLmumvgobSVLTXlkO+3JStGb1QcYSukwl/I+XvFM0iFYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","last_reissued_at":"2026-07-05T10:43:56.116779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:56.116779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"David Harwath, Jeongsoo Choi, Joon Son Chung, Kim Sung-Bin, Puyuan Peng, Tae-Hyun Oh","submitted_at":"2025-04-03T08:24:47Z","abstract_excerpt":"We present VoiceCraft-Dub, a novel approach for automated video dubbing that synthesizes high-quality speech from text and facial cues. This task has broad applications in filmmaking, multimedia creation, and assisting voice-impaired individuals. Building on the success of Neural Codec Language Models (NCLMs) for speech synthesis, our method extends their capabilities by incorporating video features, ensuring that synthesized speech is time-synchronized and expressively aligned with facial movements while preserving natural prosody. To inject visual cues, we design adapters to align facial fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02386","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/2504.02386/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":"2504.02386","created_at":"2026-07-05T10:43:56.116839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02386v1","created_at":"2026-07-05T10:43:56.116839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02386","created_at":"2026-07-05T10:43:56.116839+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNTVCG6IWNLK","created_at":"2026-07-05T10:43:56.116839+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNTVCG6IWNLKSXNI","created_at":"2026-07-05T10:43:56.116839+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNTVCG6I","created_at":"2026-07-05T10:43:56.116839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12292","citing_title":"CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV","json":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV.json","graph_json":"https://pith.science/api/pith-number/SNTVCG6IWNLKSXNINH2FT4D2GV/graph.json","events_json":"https://pith.science/api/pith-number/SNTVCG6IWNLKSXNINH2FT4D2GV/events.json","paper":"https://pith.science/paper/SNTVCG6I"},"agent_actions":{"view_html":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV","download_json":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV.json","view_paper":"https://pith.science/paper/SNTVCG6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02386&json=true","fetch_graph":"https://pith.science/api/pith-number/SNTVCG6IWNLKSXNINH2FT4D2GV/graph.json","fetch_events":"https://pith.science/api/pith-number/SNTVCG6IWNLKSXNINH2FT4D2GV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/action/storage_attestation","attest_author":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/action/author_attestation","sign_citation":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/action/citation_signature","submit_replication":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/action/replication_record"}},"created_at":"2026-07-05T10:43:56.116839+00:00","updated_at":"2026-07-05T10:43:56.116839+00:00"}