{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ULKLFM6OZC6PW2Y5XXAHF4BFHS","short_pith_number":"pith:ULKLFM6O","schema_version":"1.0","canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","source":{"kind":"arxiv","id":"1811.05250","version":2},"attestation_state":"computed","paper":{"title":"Modality Attention for End-to-End Audio-visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jia Jia, Pan Zhou, Wei Chen, Wenwen Yang, Yanfeng Wang","submitted_at":"2018-11-13T12:28:03Z","abstract_excerpt":"Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the di"},"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":"1811.05250","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-13T12:28:03Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"e37cc680563d85eb4f85cadb90e1d35760396f6ff61e94f23b8accee2c4f95fd","abstract_canon_sha256":"07d7730b3755c2f29110e93f8dbe7b0e981acc0e344cdf27fde6ae5e9686cd81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:59.145102Z","signature_b64":"9dP9LPEUZB2K3qS0f8p6XCSDVHInzzM/Rj7SZ+jCNIy0diZ0D0lSCdFOdhpjhFFhSEsOhPCkBLljpbdVi9QCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2d4b2b3cec8bcfb6b1dbdc072f0253caaca01424037dff2470aa362ad6703b4","last_reissued_at":"2026-05-17T23:47:59.144542Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:59.144542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modality Attention for End-to-End Audio-visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jia Jia, Pan Zhou, Wei Chen, Wenwen Yang, Yanfeng Wang","submitted_at":"2018-11-13T12:28:03Z","abstract_excerpt":"Audio-visual speech recognition (AVSR) system is thought to be one of the most promising solutions for robust speech recognition, especially in noisy environment. In this paper, we propose a novel multimodal attention based method for audio-visual speech recognition which could automatically learn the fused representation from both modalities based on their importance. Our method is realized using state-of-the-art sequence-to-sequence (Seq2seq) architectures. Experimental results show that relative improvements from 2% up to 36% over the auditory modality alone are obtained depending on the di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05250","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":""},"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":"1811.05250","created_at":"2026-05-17T23:47:59.144626+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.05250v2","created_at":"2026-05-17T23:47:59.144626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05250","created_at":"2026-05-17T23:47:59.144626+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULKLFM6OZC6P","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULKLFM6OZC6PW2Y5","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULKLFM6O","created_at":"2026-05-18T12:32:56.356000+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/ULKLFM6OZC6PW2Y5XXAHF4BFHS","json":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS.json","graph_json":"https://pith.science/api/pith-number/ULKLFM6OZC6PW2Y5XXAHF4BFHS/graph.json","events_json":"https://pith.science/api/pith-number/ULKLFM6OZC6PW2Y5XXAHF4BFHS/events.json","paper":"https://pith.science/paper/ULKLFM6O"},"agent_actions":{"view_html":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS","download_json":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS.json","view_paper":"https://pith.science/paper/ULKLFM6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.05250&json=true","fetch_graph":"https://pith.science/api/pith-number/ULKLFM6OZC6PW2Y5XXAHF4BFHS/graph.json","fetch_events":"https://pith.science/api/pith-number/ULKLFM6OZC6PW2Y5XXAHF4BFHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/action/storage_attestation","attest_author":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/action/author_attestation","sign_citation":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/action/citation_signature","submit_replication":"https://pith.science/pith/ULKLFM6OZC6PW2Y5XXAHF4BFHS/action/replication_record"}},"created_at":"2026-05-17T23:47:59.144626+00:00","updated_at":"2026-05-17T23:47:59.144626+00:00"}