{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:CO5KJ6DGYBGCYSTBKT7V3A76VR","short_pith_number":"pith:CO5KJ6DG","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"},"canonical_sha256":"13baa4f866c04c2c4a6154ff5d83feac7ea8bfbe15ad003107dfab89574588b3","source":{"kind":"arxiv","id":"1501.05396","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.05396","created_at":"2026-05-18T02:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"1501.05396v1","created_at":"2026-05-18T02:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05396","created_at":"2026-05-18T02:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"CO5KJ6DGYBGC","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CO5KJ6DGYBGCYSTB","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CO5KJ6DG","created_at":"2026-05-18T12:29:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:CO5KJ6DGYBGCYSTBKT7V3A76VR","target":"record","payload":{"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"},"canonical_sha256":"13baa4f866c04c2c4a6154ff5d83feac7ea8bfbe15ad003107dfab89574588b3","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"},"source_kind":"arxiv","source_id":"1501.05396","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXLxy4Z2ge8m2VrcmIuxzdRISfAJrIpm0pPpxdIjG31P77mx7rhAD1sF2ki5LS+b4UHNmT00cz3YHEQKp+3nCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:31:27.017376Z"},"content_sha256":"939a35a1d744afc0ca213e4efbe9d4523b048e52108763592a911eca387e7475","schema_version":"1.0","event_id":"sha256:939a35a1d744afc0ca213e4efbe9d4523b048e52108763592a911eca387e7475"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:CO5KJ6DGYBGCYSTBKT7V3A76VR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XlbCSIr3Jiw0eTwlTI9POsaiU/Uejwk4Ed8qcWoyUAcapN3W5h0L3eUiDbqQAD/LQGeXUWl3q9YKkDvDAbOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T03:31:27.017737Z"},"content_sha256":"d147c47585a9f00bbf6e0d087a6f09afa99cd48d39a1331c73977fdbe71689fc","schema_version":"1.0","event_id":"sha256:d147c47585a9f00bbf6e0d087a6f09afa99cd48d39a1331c73977fdbe71689fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/bundle.json","state_url":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/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":"2026-06-04T03:31:27Z","links":{"resolver":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR","bundle":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/bundle.json","state":"https://pith.science/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CO5KJ6DGYBGCYSTBKT7V3A76VR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:CO5KJ6DGYBGCYSTBKT7V3A76VR","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":"0e59f48ea1f7d0e5d3a517a60cb467f7a02cf5da8ef806f2d3184bde4ad101c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-01-22T05:25:33Z","title_canon_sha256":"2ccb66deb3f9ae7a9d5455e0398833bcae64fa446584c8375cc614fbce001481"},"schema_version":"1.0","source":{"id":"1501.05396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.05396","created_at":"2026-05-18T02:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"1501.05396v1","created_at":"2026-05-18T02:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05396","created_at":"2026-05-18T02:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"CO5KJ6DGYBGC","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"CO5KJ6DGYBGCYSTB","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"CO5KJ6DG","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:d147c47585a9f00bbf6e0d087a6f09afa99cd48d39a1331c73977fdbe71689fc","target":"graph","created_at":"2026-05-18T02:28:54Z","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":"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","authors_text":"Etienne Marcheret, Vaibhava Goel, Youssef Mroueh","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-01-22T05:25:33Z","title":"Deep Multimodal Learning for Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.05396","kind":"arxiv","version":1},"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":"sha256:939a35a1d744afc0ca213e4efbe9d4523b048e52108763592a911eca387e7475","target":"record","created_at":"2026-05-18T02:28:54Z","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":"0e59f48ea1f7d0e5d3a517a60cb467f7a02cf5da8ef806f2d3184bde4ad101c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-01-22T05:25:33Z","title_canon_sha256":"2ccb66deb3f9ae7a9d5455e0398833bcae64fa446584c8375cc614fbce001481"},"schema_version":"1.0","source":{"id":"1501.05396","kind":"arxiv","version":1}},"canonical_sha256":"13baa4f866c04c2c4a6154ff5d83feac7ea8bfbe15ad003107dfab89574588b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13baa4f866c04c2c4a6154ff5d83feac7ea8bfbe15ad003107dfab89574588b3","first_computed_at":"2026-05-18T02:28:54.689640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:28:54.689640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hHHmPlyD12yr1k/ikWUTaEimZG3emrBl9gpQAj7Sk0iLhgmRJ1KgQ1eohuwJTDsv1m+8774uaU4zcTjGLOLNDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:28:54.689993Z","signed_message":"canonical_sha256_bytes"},"source_id":"1501.05396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:939a35a1d744afc0ca213e4efbe9d4523b048e52108763592a911eca387e7475","sha256:d147c47585a9f00bbf6e0d087a6f09afa99cd48d39a1331c73977fdbe71689fc"],"state_sha256":"fba6ffae3bd65d6ba6d7a34a5a6b7039f2124ed808e7f081f4d51c873302ce08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtHs/jRfUsX78ltVbmzP00uQO/wgucv6LKo2kemNJJ7LQZMYNoptG8Rg4Y4zQMYiN0moM68Tdv77EygdSzAsCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T03:31:27.019747Z","bundle_sha256":"3c1aba510082fc319dc41966269af8de524b7e58f19f7daab28da3e2bef3cd49"}}