{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XPGEWFMMFLANOIKVLVKB4ANINC","short_pith_number":"pith:XPGEWFMM","canonical_record":{"source":{"id":"1808.00060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-07-31T20:12:15Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"aa934e60efcee4f052aa32823d5ca66549dd06dcf03066bf808ce7419b5a76d9","abstract_canon_sha256":"c2d077bf74c691c79f89f7852df02b3abac7adcb7cd1551473c3a9e763b81bc0"},"schema_version":"1.0"},"canonical_sha256":"bbcc4b158c2ac0d721555d541e01a868ad7ba46ab29782e0a3360d2408900673","source":{"kind":"arxiv","id":"1808.00060","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00060","created_at":"2026-05-18T00:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00060v1","created_at":"2026-05-18T00:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00060","created_at":"2026-05-18T00:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"XPGEWFMMFLAN","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XPGEWFMMFLANOIKV","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XPGEWFMM","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XPGEWFMMFLANOIKVLVKB4ANINC","target":"record","payload":{"canonical_record":{"source":{"id":"1808.00060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-07-31T20:12:15Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"aa934e60efcee4f052aa32823d5ca66549dd06dcf03066bf808ce7419b5a76d9","abstract_canon_sha256":"c2d077bf74c691c79f89f7852df02b3abac7adcb7cd1551473c3a9e763b81bc0"},"schema_version":"1.0"},"canonical_sha256":"bbcc4b158c2ac0d721555d541e01a868ad7ba46ab29782e0a3360d2408900673","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:01.219091Z","signature_b64":"mwX5zCWGvNZHkdNGaYZ/n7s1d33Apv5lC7Xw/4dHluz+cG5BKDNAxUkEFWmfTxwDqIM1xNi641IBZMa2lAaOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbcc4b158c2ac0d721555d541e01a868ad7ba46ab29782e0a3360d2408900673","last_reissued_at":"2026-05-18T00:06:01.218706Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:01.218706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.00060","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":"2026-05-18T00:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AwhWb76JockYNN28XlzHsxfzV5MHNowxrDnINT7/HZ5Gof6d6lPlKr2Od7piqhxE9oHzjHldLbCj5eZdJHtYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T13:53:49.205920Z"},"content_sha256":"ca355e30a40bef2e2a46d24add4d46ef241ca2e4513a9bc6313812f2e7f6ccbc","schema_version":"1.0","event_id":"sha256:ca355e30a40bef2e2a46d24add4d46ef241ca2e4513a9bc6313812f2e7f6ccbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XPGEWFMMFLANOIKVLVKB4ANINC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DNN driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ahsan Adeel, Amir Hussain, Jon Barker, Mandar Gogate, Ricard Marxer","submitted_at":"2018-07-31T20:12:15Z","abstract_excerpt":"Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on target speaker while filtering out other noises. In this study, we propose a novel deep neural network (DNN) based audiovisual (AV) mask estimation model. The proposed AV mask estimation model contextually integrates the temporal dynamics of both audio and noise-immune visual features for improved mask estimation and speech separation. For optimal AV features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00060","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":"2026-05-18T00:06:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kca8r7u7Q3r+UxY1Xm3wTGrWgf0/9VpvavSf6JWUHU8rjbS9Ihle9Xz6LjGatWMJ1Bdlkyd0peM87qjlXCuuDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-21T13:53:49.206263Z"},"content_sha256":"3a88c8f488bb324cd37eff08e0afce2800d2319a8997633a2a7c8baeb182062e","schema_version":"1.0","event_id":"sha256:3a88c8f488bb324cd37eff08e0afce2800d2319a8997633a2a7c8baeb182062e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPGEWFMMFLANOIKVLVKB4ANINC/bundle.json","state_url":"https://pith.science/pith/XPGEWFMMFLANOIKVLVKB4ANINC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPGEWFMMFLANOIKVLVKB4ANINC/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":"2026-06-21T13:53:49Z","links":{"resolver":"https://pith.science/pith/XPGEWFMMFLANOIKVLVKB4ANINC","bundle":"https://pith.science/pith/XPGEWFMMFLANOIKVLVKB4ANINC/bundle.json","state":"https://pith.science/pith/XPGEWFMMFLANOIKVLVKB4ANINC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPGEWFMMFLANOIKVLVKB4ANINC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XPGEWFMMFLANOIKVLVKB4ANINC","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":"c2d077bf74c691c79f89f7852df02b3abac7adcb7cd1551473c3a9e763b81bc0","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-07-31T20:12:15Z","title_canon_sha256":"aa934e60efcee4f052aa32823d5ca66549dd06dcf03066bf808ce7419b5a76d9"},"schema_version":"1.0","source":{"id":"1808.00060","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.00060","created_at":"2026-05-18T00:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.00060v1","created_at":"2026-05-18T00:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.00060","created_at":"2026-05-18T00:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"XPGEWFMMFLAN","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XPGEWFMMFLANOIKV","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XPGEWFMM","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:3a88c8f488bb324cd37eff08e0afce2800d2319a8997633a2a7c8baeb182062e","target":"graph","created_at":"2026-05-18T00:06:01Z","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":"Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on target speaker while filtering out other noises. In this study, we propose a novel deep neural network (DNN) based audiovisual (AV) mask estimation model. The proposed AV mask estimation model contextually integrates the temporal dynamics of both audio and noise-immune visual features for improved mask estimation and speech separation. For optimal AV features","authors_text":"Ahsan Adeel, Amir Hussain, Jon Barker, Mandar Gogate, Ricard Marxer","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-07-31T20:12:15Z","title":"DNN driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.00060","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:ca355e30a40bef2e2a46d24add4d46ef241ca2e4513a9bc6313812f2e7f6ccbc","target":"record","created_at":"2026-05-18T00:06:01Z","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":"c2d077bf74c691c79f89f7852df02b3abac7adcb7cd1551473c3a9e763b81bc0","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-07-31T20:12:15Z","title_canon_sha256":"aa934e60efcee4f052aa32823d5ca66549dd06dcf03066bf808ce7419b5a76d9"},"schema_version":"1.0","source":{"id":"1808.00060","kind":"arxiv","version":1}},"canonical_sha256":"bbcc4b158c2ac0d721555d541e01a868ad7ba46ab29782e0a3360d2408900673","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbcc4b158c2ac0d721555d541e01a868ad7ba46ab29782e0a3360d2408900673","first_computed_at":"2026-05-18T00:06:01.218706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:01.218706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mwX5zCWGvNZHkdNGaYZ/n7s1d33Apv5lC7Xw/4dHluz+cG5BKDNAxUkEFWmfTxwDqIM1xNi641IBZMa2lAaOAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:01.219091Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.00060","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca355e30a40bef2e2a46d24add4d46ef241ca2e4513a9bc6313812f2e7f6ccbc","sha256:3a88c8f488bb324cd37eff08e0afce2800d2319a8997633a2a7c8baeb182062e"],"state_sha256":"ff6e1fb126f042d9614421b56cf0c905b4b882dc086690714e203e42a10de589"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"50DVZi2TChWoRfOY3dhAla1Aczz7h2g2ZyDmV+COihQej2O5TJI51sJz6UmsqqVpg1GYiuRxiX3RaJkYyBwrBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-21T13:53:49.208235Z","bundle_sha256":"d2dd0ea310e4b9c532606b7ebb51ec23bf2e90606b545524cf289804cd9ddb39"}}