{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:CO5KJ6DGYBGCYSTBKT7V3A76VR","short_pith_number":"pith:CO5KJ6DG","schema_version":"1.0","canonical_sha256":"13baa4f866c04c2c4a6154ff5d83feac7ea8bfbe15ad003107dfab89574588b3","source":{"kind":"arxiv","id":"1501.05396","version":1},"attestation_state":"computed","paper":{"title":"Deep Multimodal Learning for Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Etienne Marcheret, Vaibhava Goel, Youssef Mroueh","submitted_at":"2015-01-22T05:25:33Z","abstract_excerpt":"In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR). First, we study an approach where uni-modal deep networks are trained separately and their final hidden layers fused to obtain a joint feature space in which another deep network is built. While the audio network alone achieves a phone error rate (PER) of $41\\%$ under clean condition on the IBM large vocabulary audio-visual studio dataset, this fusion model achieves a PER of $35.83\\%$ demonstrating the tremendous value of the visual chann"},"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":"1501.05396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-01-22T05:25:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2ccb66deb3f9ae7a9d5455e0398833bcae64fa446584c8375cc614fbce001481","abstract_canon_sha256":"0e59f48ea1f7d0e5d3a517a60cb467f7a02cf5da8ef806f2d3184bde4ad101c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:54.689993Z","signature_b64":"hHHmPlyD12yr1k/ikWUTaEimZG3emrBl9gpQAj7Sk0iLhgmRJ1KgQ1eohuwJTDsv1m+8774uaU4zcTjGLOLNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13baa4f866c04c2c4a6154ff5d83feac7ea8bfbe15ad003107dfab89574588b3","last_reissued_at":"2026-05-18T02:28:54.689640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:54.689640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multimodal Learning for Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Etienne Marcheret, Vaibhava Goel, Youssef Mroueh","submitted_at":"2015-01-22T05:25:33Z","abstract_excerpt":"In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR). First, we study an approach where uni-modal deep networks are trained separately and their final hidden layers fused to obtain a joint feature space in which another deep network is built. While the audio network alone achieves a phone error rate (PER) of $41\\%$ under clean condition on the IBM large vocabulary audio-visual studio dataset, this fusion model achieves a PER of $35.83\\%$ demonstrating the tremendous value of the visual chann"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.05396","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":"1501.05396","created_at":"2026-05-18T02:28:54.689703+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.05396v1","created_at":"2026-05-18T02:28:54.689703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05396","created_at":"2026-05-18T02:28:54.689703+00:00"},{"alias_kind":"pith_short_12","alias_value":"CO5KJ6DGYBGC","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"CO5KJ6DGYBGCYSTB","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"CO5KJ6DG","created_at":"2026-05-18T12:29:17.054201+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/CO5KJ6DGYBGCYSTBKT7V3A76VR","json":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR.json","graph_json":"https://pith.science/api/pith-number/CO5KJ6DGYBGCYSTBKT7V3A76VR/graph.json","events_json":"https://pith.science/api/pith-number/CO5KJ6DGYBGCYSTBKT7V3A76VR/events.json","paper":"https://pith.science/paper/CO5KJ6DG"},"agent_actions":{"view_html":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR","download_json":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR.json","view_paper":"https://pith.science/paper/CO5KJ6DG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.05396&json=true","fetch_graph":"https://pith.science/api/pith-number/CO5KJ6DGYBGCYSTBKT7V3A76VR/graph.json","fetch_events":"https://pith.science/api/pith-number/CO5KJ6DGYBGCYSTBKT7V3A76VR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/action/storage_attestation","attest_author":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/action/author_attestation","sign_citation":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/action/citation_signature","submit_replication":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/action/replication_record"}},"created_at":"2026-05-18T02:28:54.689703+00:00","updated_at":"2026-05-18T02:28:54.689703+00:00"}