{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6QJYHELBSCI7KGCZ6QWN6ILGB","short_pith_number":"pith:P6QJYHEL","schema_version":"1.0","canonical_sha256":"7fa09c1c8b0c848fa8c2cfa166f90b3048887633ae6eb386e49bad9e6b427122","source":{"kind":"arxiv","id":"2505.01263","version":2},"attestation_state":"computed","paper":{"title":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Amin Beheshti, Anton van den Hengel, Gaoxiang Cong, Jiadong Pan, Liang Li, Qingming Huang, Yuankai Qi, Zhedong Zhang","submitted_at":"2025-05-02T13:30:19Z","abstract_excerpt":"Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in both temporal and emotional aspects while preserving the vocal timbre of a given brief reference audio. Existing methods focus primarily on reducing the word error rate while ignoring the importance of lip-sync and acoustic quality. To address these issues, we propose a large language model (LLM) based flow matching architecture for dubbing, named FlowDubber, which achieves high-quality audio-visual sync and pronunciation by incorporating a large speech language model and dual contrastive aligning while"},"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":"2505.01263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-05-02T13:30:19Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"14991e45300fcf32b327daa872734406610f28e5b0228aa6a75e844741520500","abstract_canon_sha256":"0cfeff23af427bfa554ba3edd39fe83775b2d465d697632a669d31d7aef6486a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:28.352535Z","signature_b64":"7rOZhNMygVgQ8koF7uLApRj1q1PhKL2CKVPjIGiBi5Z2RQv3UggGC0CnHiZYTVwrlqOVu/DrAQRWs4PJVNEHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fa09c1c8b0c848fa8c2cfa166f90b3048887633ae6eb386e49bad9e6b427122","last_reissued_at":"2026-07-05T11:58:28.352017Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:28.352017Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Amin Beheshti, Anton van den Hengel, Gaoxiang Cong, Jiadong Pan, Liang Li, Qingming Huang, Yuankai Qi, Zhedong Zhang","submitted_at":"2025-05-02T13:30:19Z","abstract_excerpt":"Movie Dubbing aims to convert scripts into speeches that align with the given movie clip in both temporal and emotional aspects while preserving the vocal timbre of a given brief reference audio. Existing methods focus primarily on reducing the word error rate while ignoring the importance of lip-sync and acoustic quality. To address these issues, we propose a large language model (LLM) based flow matching architecture for dubbing, named FlowDubber, which achieves high-quality audio-visual sync and pronunciation by incorporating a large speech language model and dual contrastive aligning while"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01263","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/2505.01263/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":"2505.01263","created_at":"2026-07-05T11:58:28.352079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01263v2","created_at":"2026-07-05T11:58:28.352079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01263","created_at":"2026-07-05T11:58:28.352079+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6QJYHELBSCI","created_at":"2026-07-05T11:58:28.352079+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6QJYHELBSCI7KGC","created_at":"2026-07-05T11:58:28.352079+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6QJYHEL","created_at":"2026-07-05T11:58:28.352079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09111","citing_title":"PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB","json":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB.json","graph_json":"https://pith.science/api/pith-number/P6QJYHELBSCI7KGCZ6QWN6ILGB/graph.json","events_json":"https://pith.science/api/pith-number/P6QJYHELBSCI7KGCZ6QWN6ILGB/events.json","paper":"https://pith.science/paper/P6QJYHEL"},"agent_actions":{"view_html":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB","download_json":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB.json","view_paper":"https://pith.science/paper/P6QJYHEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01263&json=true","fetch_graph":"https://pith.science/api/pith-number/P6QJYHELBSCI7KGCZ6QWN6ILGB/graph.json","fetch_events":"https://pith.science/api/pith-number/P6QJYHELBSCI7KGCZ6QWN6ILGB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB/action/storage_attestation","attest_author":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB/action/author_attestation","sign_citation":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB/action/citation_signature","submit_replication":"https://pith.science/pith/P6QJYHELBSCI7KGCZ6QWN6ILGB/action/replication_record"}},"created_at":"2026-07-05T11:58:28.352079+00:00","updated_at":"2026-07-05T11:58:28.352079+00:00"}