{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LX676QJWKUBJSZ2KVWZLBOA6MW","short_pith_number":"pith:LX676QJW","schema_version":"1.0","canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","source":{"kind":"arxiv","id":"1804.11127","version":1},"attestation_state":"computed","paper":{"title":"Investigations on End-to-End Audiovisual Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Juergen Schmidhuber, Michael Wand, Ngoc Thang Vu","submitted_at":"2018-04-30T11:27:26Z","abstract_excerpt":"Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separately model the process of decision fusion as in conventional (e.g. HMM-based) systems. The fusion system outperforms single-modality recognition under all noise conditions. Investigation of the saliency of the input features shows that the neural network automatically adapts to different noise levels i"},"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":"1804.11127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-30T11:27:26Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"ea35fb20027946b5d81c758e43d8070705b93c9df95d0c4206b791cfa84eb2c3","abstract_canon_sha256":"61a1c8d9116fb3b2af0a45c129a8ee41e8da19b02ae5f5c2973322a608209679"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:14.560717Z","signature_b64":"Th6mWXd3FqnlZGT0yeyUeWrSEEUVZ5qGIue30FJddA4cFVFeHz63WYZpXSxIWf0XVuIxdyUFbErkd5oGCSn2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dfdff4136550299674aadb2b0b81e659b01c01d3bccb3c3263919581de7b061","last_reissued_at":"2026-05-18T00:17:14.560006Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:14.560006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigations on End-to-End Audiovisual Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CV","authors_text":"Juergen Schmidhuber, Michael Wand, Ngoc Thang Vu","submitted_at":"2018-04-30T11:27:26Z","abstract_excerpt":"Audiovisual speech recognition (AVSR) is a method to alleviate the adverse effect of noise in the acoustic signal. Leveraging recent developments in deep neural network-based speech recognition, we present an AVSR neural network architecture which is trained end-to-end, without the need to separately model the process of decision fusion as in conventional (e.g. HMM-based) systems. The fusion system outperforms single-modality recognition under all noise conditions. Investigation of the saliency of the input features shows that the neural network automatically adapts to different noise levels i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.11127","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":""},"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":"1804.11127","created_at":"2026-05-18T00:17:14.560096+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.11127v1","created_at":"2026-05-18T00:17:14.560096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.11127","created_at":"2026-05-18T00:17:14.560096+00:00"},{"alias_kind":"pith_short_12","alias_value":"LX676QJWKUBJ","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LX676QJWKUBJSZ2K","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LX676QJW","created_at":"2026-05-18T12:32:37.024351+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/LX676QJWKUBJSZ2KVWZLBOA6MW","json":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW.json","graph_json":"https://pith.science/api/pith-number/LX676QJWKUBJSZ2KVWZLBOA6MW/graph.json","events_json":"https://pith.science/api/pith-number/LX676QJWKUBJSZ2KVWZLBOA6MW/events.json","paper":"https://pith.science/paper/LX676QJW"},"agent_actions":{"view_html":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW","download_json":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW.json","view_paper":"https://pith.science/paper/LX676QJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.11127&json=true","fetch_graph":"https://pith.science/api/pith-number/LX676QJWKUBJSZ2KVWZLBOA6MW/graph.json","fetch_events":"https://pith.science/api/pith-number/LX676QJWKUBJSZ2KVWZLBOA6MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/action/storage_attestation","attest_author":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/action/author_attestation","sign_citation":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/action/citation_signature","submit_replication":"https://pith.science/pith/LX676QJWKUBJSZ2KVWZLBOA6MW/action/replication_record"}},"created_at":"2026-05-18T00:17:14.560096+00:00","updated_at":"2026-05-18T00:17:14.560096+00:00"}