{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HFUC5MYKO2LCRLCWTDS5T34TVR","short_pith_number":"pith:HFUC5MYK","schema_version":"1.0","canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","source":{"kind":"arxiv","id":"2203.07996","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Helong Zhou, Peiyu Chen, Xichen Pan, Xinbing Wang, Yichen Gong, Zhouhan Lin","submitted_at":"2022-02-24T15:12:17Z","abstract_excerpt":"Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the m"},"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":"2203.07996","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-24T15:12:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"912f4396d7c71458c26d1b2874298729317fd1d0eb2fce3f71bb784416743662","abstract_canon_sha256":"80c9c19439b6e735a4457db771d111a4a7f4b733a972419a6ba316fe13ceb809"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:42.986268Z","signature_b64":"SR9GUYOqGkKYNajYGKy10kO5bprgNcBI6dqFo8nR5JPUYPShCpf8zZa4mzhkX/m/bVmRqNcMxh02vFW0PKZ4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39682eb30a769628ac5698e5d9ef93ac787fe4d21bf4303b43152dac4a22aad7","last_reissued_at":"2026-07-05T04:08:42.985917Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:42.985917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Helong Zhou, Peiyu Chen, Xichen Pan, Xinbing Wang, Yichen Gong, Zhouhan Lin","submitted_at":"2022-02-24T15:12:17Z","abstract_excerpt":"Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.07996","kind":"arxiv","version":2},"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/2203.07996/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":"2203.07996","created_at":"2026-07-05T04:08:42.985971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.07996v2","created_at":"2026-07-05T04:08:42.985971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.07996","created_at":"2026-07-05T04:08:42.985971+00:00"},{"alias_kind":"pith_short_12","alias_value":"HFUC5MYKO2LC","created_at":"2026-07-05T04:08:42.985971+00:00"},{"alias_kind":"pith_short_16","alias_value":"HFUC5MYKO2LCRLCW","created_at":"2026-07-05T04:08:42.985971+00:00"},{"alias_kind":"pith_short_8","alias_value":"HFUC5MYK","created_at":"2026-07-05T04:08:42.985971+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/HFUC5MYKO2LCRLCWTDS5T34TVR","json":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR.json","graph_json":"https://pith.science/api/pith-number/HFUC5MYKO2LCRLCWTDS5T34TVR/graph.json","events_json":"https://pith.science/api/pith-number/HFUC5MYKO2LCRLCWTDS5T34TVR/events.json","paper":"https://pith.science/paper/HFUC5MYK"},"agent_actions":{"view_html":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR","download_json":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR.json","view_paper":"https://pith.science/paper/HFUC5MYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.07996&json=true","fetch_graph":"https://pith.science/api/pith-number/HFUC5MYKO2LCRLCWTDS5T34TVR/graph.json","fetch_events":"https://pith.science/api/pith-number/HFUC5MYKO2LCRLCWTDS5T34TVR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/action/storage_attestation","attest_author":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/action/author_attestation","sign_citation":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/action/citation_signature","submit_replication":"https://pith.science/pith/HFUC5MYKO2LCRLCWTDS5T34TVR/action/replication_record"}},"created_at":"2026-07-05T04:08:42.985971+00:00","updated_at":"2026-07-05T04:08:42.985971+00:00"}