{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3IXN6SWTCPYIIXMOPZS2G7SWGF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"87fefda7944e39510b62c317664e75a48e59c8d22e292a5df3cae543876c0b90","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-03T09:13:57Z","title_canon_sha256":"3433c9e5a923dda2ace7e055fe4e18f2fb40d9ef88d4461b12c3236a643f5347"},"schema_version":"1.0","source":{"id":"2307.01233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.01233","created_at":"2026-07-05T06:27:53Z"},{"alias_kind":"arxiv_version","alias_value":"2307.01233v1","created_at":"2026-07-05T06:27:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01233","created_at":"2026-07-05T06:27:53Z"},{"alias_kind":"pith_short_12","alias_value":"3IXN6SWTCPYI","created_at":"2026-07-05T06:27:53Z"},{"alias_kind":"pith_short_16","alias_value":"3IXN6SWTCPYIIXMO","created_at":"2026-07-05T06:27:53Z"},{"alias_kind":"pith_short_8","alias_value":"3IXN6SWT","created_at":"2026-07-05T06:27:53Z"}],"graph_snapshots":[{"event_id":"sha256:9ca04e9b7dbdbe44937eee50818b45984845cb89a3cf05ee37bd78eddb20211d","target":"graph","created_at":"2026-07-05T06:27:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.01233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Significant progress has been made in speaker dependent Lip-to-Speech synthesis, which aims to generate speech from silent videos of talking faces. Current state-of-the-art approaches primarily employ non-autoregressive sequence-to-sequence architectures to directly predict mel-spectrograms or audio waveforms from lip representations. We hypothesize that the direct mel-prediction hampers training/model efficiency due to the entanglement of speech content with ambient information and speaker characteristics. To this end, we propose RobustL2S, a modularized framework for Lip-to-Speech synthesis.","authors_text":"Neha Sahipjohn, Neil Shah, Vineet Gandhi, Vishal Tambrahalli","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-03T09:13:57Z","title":"RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01233","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39ae4b7b5d9c8f6f175d486d39d748cce5b677aa24d394ea0ae916b8c8694a42","target":"record","created_at":"2026-07-05T06:27:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"87fefda7944e39510b62c317664e75a48e59c8d22e292a5df3cae543876c0b90","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-03T09:13:57Z","title_canon_sha256":"3433c9e5a923dda2ace7e055fe4e18f2fb40d9ef88d4461b12c3236a643f5347"},"schema_version":"1.0","source":{"id":"2307.01233","kind":"arxiv","version":1}},"canonical_sha256":"da2edf4ad313f0845d8e7e65a37e563151bf6db041f0944b62f8b3f614f9c6e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da2edf4ad313f0845d8e7e65a37e563151bf6db041f0944b62f8b3f614f9c6e3","first_computed_at":"2026-07-05T06:27:53.386845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:27:53.386845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cMil/AccRGAA6tpqQ6M5eQwnJQ7CuNYjDoDkqZmuO0hkeHwnlH5Cra/riszCK9AGzqEMpSwjMj2MK57VSMT9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:27:53.387302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.01233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39ae4b7b5d9c8f6f175d486d39d748cce5b677aa24d394ea0ae916b8c8694a42","sha256:9ca04e9b7dbdbe44937eee50818b45984845cb89a3cf05ee37bd78eddb20211d"],"state_sha256":"48a8483bf10205f0aefedc506f23875e53478af1740ba8cfa79715f77c322473"}