{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KITKBZ4KXASOFF24LKHUVK4UNW","short_pith_number":"pith:KITKBZ4K","schema_version":"1.0","canonical_sha256":"5226a0e78ab824e2975c5a8f4aab946db57fd60ca04f4b6e3576b8a500122d24","source":{"kind":"arxiv","id":"2106.09171","version":1},"attestation_state":"computed","paper":{"title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Bj\\\"orn W. Schuller, Maja Pantic, Pingchuan Ma, Rodrigo Mira, Stavros Petridis","submitted_at":"2021-06-16T23:20:06Z","abstract_excerpt":"The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac"},"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":"2106.09171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T23:20:06Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"f49ee7c7d3f7bf2452fea69508b945b5e0c58d4db543bf6dd88c291d82e8e6d1","abstract_canon_sha256":"db338ca29162ca7dc5cf8f9fb8f404cf4196faef5cc84a2bbe83af695c22cc9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:13.017081Z","signature_b64":"nArqiO9UhkBijlF4EyRCcZZjhFqGQJf8V+4qYU7B5b/xlnlI5TwW2XMl6qiaE/nUeHzcg8hx7o7lfPr5I4kfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5226a0e78ab824e2975c5a8f4aab946db57fd60ca04f4b6e3576b8a500122d24","last_reissued_at":"2026-07-05T02:50:13.016606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:13.016606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Bj\\\"orn W. Schuller, Maja Pantic, Pingchuan Ma, Rodrigo Mira, Stavros Petridis","submitted_at":"2021-06-16T23:20:06Z","abstract_excerpt":"The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09171","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/2106.09171/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":"2106.09171","created_at":"2026-07-05T02:50:13.016665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09171v1","created_at":"2026-07-05T02:50:13.016665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09171","created_at":"2026-07-05T02:50:13.016665+00:00"},{"alias_kind":"pith_short_12","alias_value":"KITKBZ4KXASO","created_at":"2026-07-05T02:50:13.016665+00:00"},{"alias_kind":"pith_short_16","alias_value":"KITKBZ4KXASOFF24","created_at":"2026-07-05T02:50:13.016665+00:00"},{"alias_kind":"pith_short_8","alias_value":"KITKBZ4K","created_at":"2026-07-05T02:50:13.016665+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/KITKBZ4KXASOFF24LKHUVK4UNW","json":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW.json","graph_json":"https://pith.science/api/pith-number/KITKBZ4KXASOFF24LKHUVK4UNW/graph.json","events_json":"https://pith.science/api/pith-number/KITKBZ4KXASOFF24LKHUVK4UNW/events.json","paper":"https://pith.science/paper/KITKBZ4K"},"agent_actions":{"view_html":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW","download_json":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW.json","view_paper":"https://pith.science/paper/KITKBZ4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09171&json=true","fetch_graph":"https://pith.science/api/pith-number/KITKBZ4KXASOFF24LKHUVK4UNW/graph.json","fetch_events":"https://pith.science/api/pith-number/KITKBZ4KXASOFF24LKHUVK4UNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW/action/storage_attestation","attest_author":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW/action/author_attestation","sign_citation":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW/action/citation_signature","submit_replication":"https://pith.science/pith/KITKBZ4KXASOFF24LKHUVK4UNW/action/replication_record"}},"created_at":"2026-07-05T02:50:13.016665+00:00","updated_at":"2026-07-05T02:50:13.016665+00:00"}