{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RHRFVDOP6GYIOES5KJV5AXP3OL","short_pith_number":"pith:RHRFVDOP","schema_version":"1.0","canonical_sha256":"89e25a8dcff1b087125d526bd05dfb72ff9b5188d92d5997402d08ea02b27377","source":{"kind":"arxiv","id":"2407.07825","version":1},"attestation_state":"computed","paper":{"title":"RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Honglie Chen, Maja Pantic, Rodrigo Mira, Stavros Petridis","submitted_at":"2024-07-10T16:49:23Z","abstract_excerpt":"In this paper, we aim to generate clean speech frame by frame from a live video stream and a noisy audio stream without relying on future inputs. To this end, we propose RT-LA-VocE, which completely re-designs every component of LA-VocE, a state-of-the-art non-causal audio-visual speech enhancement model, to perform causal real-time inference with a 40ms input frame. We do so by devising new visual and audio encoders that rely solely on past frames, replacing the Transformer encoder with the Emformer, and designing a new causal neural vocoder C-HiFi-GAN. On the popular AVSpeech dataset, we sho"},"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":"2407.07825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T16:49:23Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"36a34a3b177dc0c80266f1f616d4c1dd68cf22f118a33bd7db261f92cd294320","abstract_canon_sha256":"65956dea83d501607fd92ef7c9f306121bbabed3aa7155e4c11b9bb9b0827d3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:25.862934Z","signature_b64":"5JJ7ehkst6J2mN/zAPHkZy6PMV/XUVFgzApJ89YMio8BZjNFXzezNO/v914RaHIA9VaNz8WMLyKWf/O9hXQIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89e25a8dcff1b087125d526bd05dfb72ff9b5188d92d5997402d08ea02b27377","last_reissued_at":"2026-07-05T08:42:25.862422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:25.862422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Honglie Chen, Maja Pantic, Rodrigo Mira, Stavros Petridis","submitted_at":"2024-07-10T16:49:23Z","abstract_excerpt":"In this paper, we aim to generate clean speech frame by frame from a live video stream and a noisy audio stream without relying on future inputs. To this end, we propose RT-LA-VocE, which completely re-designs every component of LA-VocE, a state-of-the-art non-causal audio-visual speech enhancement model, to perform causal real-time inference with a 40ms input frame. We do so by devising new visual and audio encoders that rely solely on past frames, replacing the Transformer encoder with the Emformer, and designing a new causal neural vocoder C-HiFi-GAN. On the popular AVSpeech dataset, we sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07825","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/2407.07825/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":"2407.07825","created_at":"2026-07-05T08:42:25.862503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07825v1","created_at":"2026-07-05T08:42:25.862503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07825","created_at":"2026-07-05T08:42:25.862503+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHRFVDOP6GYI","created_at":"2026-07-05T08:42:25.862503+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHRFVDOP6GYIOES5","created_at":"2026-07-05T08:42:25.862503+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHRFVDOP","created_at":"2026-07-05T08:42:25.862503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL","json":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL.json","graph_json":"https://pith.science/api/pith-number/RHRFVDOP6GYIOES5KJV5AXP3OL/graph.json","events_json":"https://pith.science/api/pith-number/RHRFVDOP6GYIOES5KJV5AXP3OL/events.json","paper":"https://pith.science/paper/RHRFVDOP"},"agent_actions":{"view_html":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL","download_json":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL.json","view_paper":"https://pith.science/paper/RHRFVDOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07825&json=true","fetch_graph":"https://pith.science/api/pith-number/RHRFVDOP6GYIOES5KJV5AXP3OL/graph.json","fetch_events":"https://pith.science/api/pith-number/RHRFVDOP6GYIOES5KJV5AXP3OL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL/action/storage_attestation","attest_author":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL/action/author_attestation","sign_citation":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL/action/citation_signature","submit_replication":"https://pith.science/pith/RHRFVDOP6GYIOES5KJV5AXP3OL/action/replication_record"}},"created_at":"2026-07-05T08:42:25.862503+00:00","updated_at":"2026-07-05T08:42:25.862503+00:00"}