{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:27BENKZVZY4KSG43V2BSNWOECJ","short_pith_number":"pith:27BENKZV","schema_version":"1.0","canonical_sha256":"d7c246ab35ce38a91b9bae8326d9c412427ee6ac27d048d5b167c0e230d31e0b","source":{"kind":"arxiv","id":"2606.05763","version":1},"attestation_state":"computed","paper":{"title":"M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cancan Li, Fei Su, Juan Liu, Ming Li","submitted_at":"2026-06-04T06:44:54Z","abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) enhances speech recognition robustness by leveraging visual cues, while real-world scenarios remain challenging due to viewpoint variation, audio distortion, and visual occlusion, which degrade modality quality and increase audio-visual asynchrony. In this paper, we propose a novel Modality-aware Multi-view Self-supervised representation framework for robust Audio-Visual Speech Recognition (M2S-AVSR). First, we introduce a multi-view representation learning encoder to learn view-invariant visual speech representations. Next, we employ a modality-aware mod"},"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":"2606.05763","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T06:44:54Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"cbf1c615785b2c226decaae3c2b3791d0aca9a9bf5f818922e1d7f31c285a9c5","abstract_canon_sha256":"a8ed605126c22cf33fe37eb2553aa3bae0362051493e727f26d19c94fa57d318"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:02.313074Z","signature_b64":"kThwvt2zRmv+ssjlvteiDC1SXQNBrRrB2yXxjVZ6dLkVAG5ZoPt87bYic9xc3XBhSIndX3owGiw+xtfnIvbWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7c246ab35ce38a91b9bae8326d9c412427ee6ac27d048d5b167c0e230d31e0b","last_reissued_at":"2026-06-05T01:15:02.312570Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:02.312570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cancan Li, Fei Su, Juan Liu, Ming Li","submitted_at":"2026-06-04T06:44:54Z","abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) enhances speech recognition robustness by leveraging visual cues, while real-world scenarios remain challenging due to viewpoint variation, audio distortion, and visual occlusion, which degrade modality quality and increase audio-visual asynchrony. In this paper, we propose a novel Modality-aware Multi-view Self-supervised representation framework for robust Audio-Visual Speech Recognition (M2S-AVSR). First, we introduce a multi-view representation learning encoder to learn view-invariant visual speech representations. Next, we employ a modality-aware mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05763","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/2606.05763/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":"2606.05763","created_at":"2026-06-05T01:15:02.312646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05763v1","created_at":"2026-06-05T01:15:02.312646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05763","created_at":"2026-06-05T01:15:02.312646+00:00"},{"alias_kind":"pith_short_12","alias_value":"27BENKZVZY4K","created_at":"2026-06-05T01:15:02.312646+00:00"},{"alias_kind":"pith_short_16","alias_value":"27BENKZVZY4KSG43","created_at":"2026-06-05T01:15:02.312646+00:00"},{"alias_kind":"pith_short_8","alias_value":"27BENKZV","created_at":"2026-06-05T01:15:02.312646+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/27BENKZVZY4KSG43V2BSNWOECJ","json":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ.json","graph_json":"https://pith.science/api/pith-number/27BENKZVZY4KSG43V2BSNWOECJ/graph.json","events_json":"https://pith.science/api/pith-number/27BENKZVZY4KSG43V2BSNWOECJ/events.json","paper":"https://pith.science/paper/27BENKZV"},"agent_actions":{"view_html":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ","download_json":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ.json","view_paper":"https://pith.science/paper/27BENKZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05763&json=true","fetch_graph":"https://pith.science/api/pith-number/27BENKZVZY4KSG43V2BSNWOECJ/graph.json","fetch_events":"https://pith.science/api/pith-number/27BENKZVZY4KSG43V2BSNWOECJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ/action/storage_attestation","attest_author":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ/action/author_attestation","sign_citation":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ/action/citation_signature","submit_replication":"https://pith.science/pith/27BENKZVZY4KSG43V2BSNWOECJ/action/replication_record"}},"created_at":"2026-06-05T01:15:02.312646+00:00","updated_at":"2026-06-05T01:15:02.312646+00:00"}