{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:V2HZEMTC65DITKHBZCKYIUB4S2","short_pith_number":"pith:V2HZEMTC","canonical_record":{"source":{"id":"1809.01728","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-09-05T20:38:48Z","cross_cats_sorted":["cs.LG","cs.SD","eess.IV","stat.ML"],"title_canon_sha256":"4e47c965a57dd4561a052593c30054d25acc5ec0a9e1063e9040947952447e91","abstract_canon_sha256":"15341a58a1a5c981e7f28aa1f303dc2e3c2813324bacc20dae27b164733902fd"},"schema_version":"1.0"},"canonical_sha256":"ae8f923262f74689a8e1c89584503c96b2832f366fd03285ddd80c48e8f4d8b3","source":{"kind":"arxiv","id":"1809.01728","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01728","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01728v3","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01728","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"V2HZEMTC65DI","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"V2HZEMTC65DITKHB","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"V2HZEMTC","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:V2HZEMTC65DITKHBZCKYIUB4S2","target":"record","payload":{"canonical_record":{"source":{"id":"1809.01728","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-09-05T20:38:48Z","cross_cats_sorted":["cs.LG","cs.SD","eess.IV","stat.ML"],"title_canon_sha256":"4e47c965a57dd4561a052593c30054d25acc5ec0a9e1063e9040947952447e91","abstract_canon_sha256":"15341a58a1a5c981e7f28aa1f303dc2e3c2813324bacc20dae27b164733902fd"},"schema_version":"1.0"},"canonical_sha256":"ae8f923262f74689a8e1c89584503c96b2832f366fd03285ddd80c48e8f4d8b3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:15.934930Z","signature_b64":"TsKkt2tneuFyuKsLa6/TGegs+Vwgr7FGvHs7Kz+0NeX8IEfKsiOiBEW8xP4QqivfOrkixsMQPURXfZCWRlGeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8f923262f74689a8e1c89584503c96b2832f366fd03285ddd80c48e8f4d8b3","last_reissued_at":"2026-05-17T23:47:15.934551Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:15.934551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.01728","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1f6/Kk5VHSgQmszkDObQdonngEq8wFDYqAzowx/AL14DnP6XVZe+bk35H81Olui5FsI2X3jzHbP8mydyN+NCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:40:10.403928Z"},"content_sha256":"3249df1c3ebdf749f6f9bf7b12ba19a81fa10acf92c9e177e0550ac672b51460","schema_version":"1.0","event_id":"sha256:3249df1c3ebdf749f6f9bf7b12ba19a81fa10acf92c9e177e0550ac672b51460"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:V2HZEMTC65DITKHBZCKYIUB4S2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.IV","stat.ML"],"primary_cat":"eess.AS","authors_text":"Christian Saam, George Sterpu, Naomi Harte","submitted_at":"2018-09-05T20:38:48Z","abstract_excerpt":"Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy that goes beyond simple feature concatenation and learns to automatically align the two modalities, leading to enhanced representations which increase the recognition accuracy in both clean and noisy conditions. We test our strategy on the TCD-TIMIT and LRS2 datasets, designed for large vocabulary continuous speech recognition, applying three types of noise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01728","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTLRSbWxDMxnl0q8y14dvO612FTbZTTbQ3rs7rDZwczv+TZH0/ppaAMI/XHIyqPkIXBKfQ+q2TNi/pufPT1WAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T08:40:10.404281Z"},"content_sha256":"1ab7d5ac1ffff47b14674988d01376c6756b67e450bf10f5005715adb143bc0c","schema_version":"1.0","event_id":"sha256:1ab7d5ac1ffff47b14674988d01376c6756b67e450bf10f5005715adb143bc0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2HZEMTC65DITKHBZCKYIUB4S2/bundle.json","state_url":"https://pith.science/pith/V2HZEMTC65DITKHBZCKYIUB4S2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2HZEMTC65DITKHBZCKYIUB4S2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T08:40:10Z","links":{"resolver":"https://pith.science/pith/V2HZEMTC65DITKHBZCKYIUB4S2","bundle":"https://pith.science/pith/V2HZEMTC65DITKHBZCKYIUB4S2/bundle.json","state":"https://pith.science/pith/V2HZEMTC65DITKHBZCKYIUB4S2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2HZEMTC65DITKHBZCKYIUB4S2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:V2HZEMTC65DITKHBZCKYIUB4S2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"15341a58a1a5c981e7f28aa1f303dc2e3c2813324bacc20dae27b164733902fd","cross_cats_sorted":["cs.LG","cs.SD","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-09-05T20:38:48Z","title_canon_sha256":"4e47c965a57dd4561a052593c30054d25acc5ec0a9e1063e9040947952447e91"},"schema_version":"1.0","source":{"id":"1809.01728","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01728","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01728v3","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01728","created_at":"2026-05-17T23:47:15Z"},{"alias_kind":"pith_short_12","alias_value":"V2HZEMTC65DI","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"V2HZEMTC65DITKHB","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"V2HZEMTC","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:1ab7d5ac1ffff47b14674988d01376c6756b67e450bf10f5005715adb143bc0c","target":"graph","created_at":"2026-05-17T23:47:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy that goes beyond simple feature concatenation and learns to automatically align the two modalities, leading to enhanced representations which increase the recognition accuracy in both clean and noisy conditions. We test our strategy on the TCD-TIMIT and LRS2 datasets, designed for large vocabulary continuous speech recognition, applying three types of noise","authors_text":"Christian Saam, George Sterpu, Naomi Harte","cross_cats":["cs.LG","cs.SD","eess.IV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-09-05T20:38:48Z","title":"Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01728","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3249df1c3ebdf749f6f9bf7b12ba19a81fa10acf92c9e177e0550ac672b51460","target":"record","created_at":"2026-05-17T23:47:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"15341a58a1a5c981e7f28aa1f303dc2e3c2813324bacc20dae27b164733902fd","cross_cats_sorted":["cs.LG","cs.SD","eess.IV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-09-05T20:38:48Z","title_canon_sha256":"4e47c965a57dd4561a052593c30054d25acc5ec0a9e1063e9040947952447e91"},"schema_version":"1.0","source":{"id":"1809.01728","kind":"arxiv","version":3}},"canonical_sha256":"ae8f923262f74689a8e1c89584503c96b2832f366fd03285ddd80c48e8f4d8b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae8f923262f74689a8e1c89584503c96b2832f366fd03285ddd80c48e8f4d8b3","first_computed_at":"2026-05-17T23:47:15.934551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:15.934551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TsKkt2tneuFyuKsLa6/TGegs+Vwgr7FGvHs7Kz+0NeX8IEfKsiOiBEW8xP4QqivfOrkixsMQPURXfZCWRlGeCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:15.934930Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.01728","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3249df1c3ebdf749f6f9bf7b12ba19a81fa10acf92c9e177e0550ac672b51460","sha256:1ab7d5ac1ffff47b14674988d01376c6756b67e450bf10f5005715adb143bc0c"],"state_sha256":"a51053ec59ce9a8e752da2a335986bfe88f6b4475b8bcfe7e26b444a385e2e7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+uFWfelGHheJfN9h4Ht39jWJ8kv5FR7KryTAgmmBkpXw3UX40chNxiz6k9N+LutIrqqngR2r8GHXiKXTN8eCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T08:40:10.406309Z","bundle_sha256":"b85cd757736cd78040d568267f3a24eeb942fb08d3574e87a11cc7ee56d9db7c"}}