{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O22JVZXXCDIP65NBPME3IDNOPV","short_pith_number":"pith:O22JVZXX","schema_version":"1.0","canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","source":{"kind":"arxiv","id":"2212.02782","version":1},"attestation_state":"computed","paper":{"title":"Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Liu, Genshun Wan, Jianqing Gao, Jia Pan, Jing-Xuan Zhang, Zhen-Hua Ling","submitted_at":"2022-12-06T06:37:38Z","abstract_excerpt":"In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher. The parameters of the teacher model are a momentum update of the student. Since our target features are generated online, AV2vec needs no iteration step like AV-HuBERT and the total training time cost is reduced to less than one-fifth. We further propose AV2vec-MLM in this study,"},"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":"2212.02782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-06T06:37:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"363268429dd685d2e01282b11ef294b9ca3172a83c5aac461a0634cecbf90c20","abstract_canon_sha256":"2e43db9806664a0ee00174050141104fec3fe6e2ca658d024af8c1534278c5e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:34.216971Z","signature_b64":"meFX+XiwJ6c5gstzDv4mW4AzVgG8sGYiI8L9m4GZqyMBO+j/Go43ei2Tv8VT4/W5Dp65s/gfVUtY2bDcAoI9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76b49ae6f710d0ff75a17b09b40dae7d7646bcdb27ee335fad1b793a286c5411","last_reissued_at":"2026-07-05T05:22:34.216480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:34.216480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Liu, Genshun Wan, Jianqing Gao, Jia Pan, Jing-Xuan Zhang, Zhen-Hua Ling","submitted_at":"2022-12-06T06:37:38Z","abstract_excerpt":"In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature regression task using the multimodal target features generated online by the teacher. The parameters of the teacher model are a momentum update of the student. Since our target features are generated online, AV2vec needs no iteration step like AV-HuBERT and the total training time cost is reduced to less than one-fifth. We further propose AV2vec-MLM in this study,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02782","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/2212.02782/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":"2212.02782","created_at":"2026-07-05T05:22:34.216536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02782v1","created_at":"2026-07-05T05:22:34.216536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02782","created_at":"2026-07-05T05:22:34.216536+00:00"},{"alias_kind":"pith_short_12","alias_value":"O22JVZXXCDIP","created_at":"2026-07-05T05:22:34.216536+00:00"},{"alias_kind":"pith_short_16","alias_value":"O22JVZXXCDIP65NB","created_at":"2026-07-05T05:22:34.216536+00:00"},{"alias_kind":"pith_short_8","alias_value":"O22JVZXX","created_at":"2026-07-05T05:22:34.216536+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/O22JVZXXCDIP65NBPME3IDNOPV","json":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV.json","graph_json":"https://pith.science/api/pith-number/O22JVZXXCDIP65NBPME3IDNOPV/graph.json","events_json":"https://pith.science/api/pith-number/O22JVZXXCDIP65NBPME3IDNOPV/events.json","paper":"https://pith.science/paper/O22JVZXX"},"agent_actions":{"view_html":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV","download_json":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV.json","view_paper":"https://pith.science/paper/O22JVZXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02782&json=true","fetch_graph":"https://pith.science/api/pith-number/O22JVZXXCDIP65NBPME3IDNOPV/graph.json","fetch_events":"https://pith.science/api/pith-number/O22JVZXXCDIP65NBPME3IDNOPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/action/storage_attestation","attest_author":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/action/author_attestation","sign_citation":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/action/citation_signature","submit_replication":"https://pith.science/pith/O22JVZXXCDIP65NBPME3IDNOPV/action/replication_record"}},"created_at":"2026-07-05T05:22:34.216536+00:00","updated_at":"2026-07-05T05:22:34.216536+00:00"}