{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L2POJS5BA6XH7XRW4CYWNTNPCO","short_pith_number":"pith:L2POJS5B","schema_version":"1.0","canonical_sha256":"5e9ee4cba107ae7fde36e0b166cdaf13abbc42522fd261d18e6cb126151cac44","source":{"kind":"arxiv","id":"2506.00740","version":1},"attestation_state":"computed","paper":{"title":"Length Aware Speech Translation for Video Dubbing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aswin Shanmugam Subramanian, Harveen Singh Chadha, Jian Xue, Jinyu Li, Rupeshkumar Mehta, Shubham Bansal, Vikas Joshi","submitted_at":"2025-05-31T23:01:50Z","abstract_excerpt":"In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video dubbing scenarios. We developed a phoneme-based end-to-end length-sensitive speech translation (LSST) model, which generates translations of varying lengths short, normal, and long using predefined tags. Additionally, we introduced length-aware beam search (LABS), an efficient approach to generate translations of different lengths in a single decoding pass. This approach maintained comparable BLEU scores compared to a "},"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":"2506.00740","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T23:01:50Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"f3097680ae65bd218bbcfbc3ce5f69c3b43828289566fd8babd972818f7b2298","abstract_canon_sha256":"9c167dfb44f8e5a4bb76afb7acee0a1d161df5b6225ceb8b997f7be3fdd40599"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:39.716992Z","signature_b64":"Eac2pvmN8Z54DYi3lmRvKAEJz6Z5ZcKzJPvLeRbSKXIHMcdRxi8KoIqoKv+oK1m2xpGFrOjfyHC5wcHtgLTnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e9ee4cba107ae7fde36e0b166cdaf13abbc42522fd261d18e6cb126151cac44","last_reissued_at":"2026-07-05T11:13:39.716503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:39.716503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Length Aware Speech Translation for Video Dubbing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aswin Shanmugam Subramanian, Harveen Singh Chadha, Jian Xue, Jinyu Li, Rupeshkumar Mehta, Shubham Bansal, Vikas Joshi","submitted_at":"2025-05-31T23:01:50Z","abstract_excerpt":"In video dubbing, aligning translated audio with the source audio is a significant challenge. Our focus is on achieving this efficiently, tailored for real-time, on-device video dubbing scenarios. We developed a phoneme-based end-to-end length-sensitive speech translation (LSST) model, which generates translations of varying lengths short, normal, and long using predefined tags. Additionally, we introduced length-aware beam search (LABS), an efficient approach to generate translations of different lengths in a single decoding pass. This approach maintained comparable BLEU scores compared to a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00740","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/2506.00740/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":"2506.00740","created_at":"2026-07-05T11:13:39.716562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00740v1","created_at":"2026-07-05T11:13:39.716562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00740","created_at":"2026-07-05T11:13:39.716562+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2POJS5BA6XH","created_at":"2026-07-05T11:13:39.716562+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2POJS5BA6XH7XRW","created_at":"2026-07-05T11:13:39.716562+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2POJS5B","created_at":"2026-07-05T11:13:39.716562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00740","citing_title":"Length Aware Speech Translation for Video Dubbing","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO","json":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO.json","graph_json":"https://pith.science/api/pith-number/L2POJS5BA6XH7XRW4CYWNTNPCO/graph.json","events_json":"https://pith.science/api/pith-number/L2POJS5BA6XH7XRW4CYWNTNPCO/events.json","paper":"https://pith.science/paper/L2POJS5B"},"agent_actions":{"view_html":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO","download_json":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO.json","view_paper":"https://pith.science/paper/L2POJS5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00740&json=true","fetch_graph":"https://pith.science/api/pith-number/L2POJS5BA6XH7XRW4CYWNTNPCO/graph.json","fetch_events":"https://pith.science/api/pith-number/L2POJS5BA6XH7XRW4CYWNTNPCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO/action/storage_attestation","attest_author":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO/action/author_attestation","sign_citation":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO/action/citation_signature","submit_replication":"https://pith.science/pith/L2POJS5BA6XH7XRW4CYWNTNPCO/action/replication_record"}},"created_at":"2026-07-05T11:13:39.716562+00:00","updated_at":"2026-07-05T11:13:39.716562+00:00"}