{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7L5A6KMTNHVFGJA4X4WM6X4TIE","short_pith_number":"pith:7L5A6KMT","canonical_record":{"source":{"id":"1906.05962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-13T23:52:16Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"title_canon_sha256":"3185457c1a11a94879e2b58538ac1573240b2f2625f36e0e3a0663026eaaf103","abstract_canon_sha256":"de107fba9a224018bbfc683dacbdb7b9a2b9216f83c2343a118f064ab23cfa0f"},"schema_version":"1.0"},"canonical_sha256":"fafa0f299369ea53241cbf2ccf5f934125e367f36d9048b6085d461de74f3df2","source":{"kind":"arxiv","id":"1906.05962","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05962","created_at":"2026-05-17T23:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05962v1","created_at":"2026-05-17T23:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05962","created_at":"2026-05-17T23:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"7L5A6KMTNHVF","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7L5A6KMTNHVFGJA4","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7L5A6KMT","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7L5A6KMTNHVFGJA4X4WM6X4TIE","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05962","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-13T23:52:16Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"title_canon_sha256":"3185457c1a11a94879e2b58538ac1573240b2f2625f36e0e3a0663026eaaf103","abstract_canon_sha256":"de107fba9a224018bbfc683dacbdb7b9a2b9216f83c2343a118f064ab23cfa0f"},"schema_version":"1.0"},"canonical_sha256":"fafa0f299369ea53241cbf2ccf5f934125e367f36d9048b6085d461de74f3df2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:20.178397Z","signature_b64":"so8XQpoQNXuC+eyOFU+caAYhRjhgPfivXPBFLGVeH43eYyla/GZLzgMPmZ0VQU1LiD3MCXvR8KMmvn/UNJ1jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fafa0f299369ea53241cbf2ccf5f934125e367f36d9048b6085d461de74f3df2","last_reissued_at":"2026-05-17T23:43:20.177792Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:20.177792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05962","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":"2026-05-17T23:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EEmRqecFqx/epRPu+pm0SvhS1lpj8T2fjllvhHc0oS4vzaFYVkX2xr+SjRsvc0/no4Jhzl0HWe5ky6lYU+4kBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:48:55.683527Z"},"content_sha256":"182434b994a8648db814c0abe34285ffa977155941e912565818d4a55d0e8781","schema_version":"1.0","event_id":"sha256:182434b994a8648db814c0abe34285ffa977155941e912565818d4a55d0e8781"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7L5A6KMTNHVFGJA4X4WM6X4TIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speaker-Targeted Audio-Visual Models for Speech Recognition in Cocktail-Party Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Guan-Lin Chao, Ian Lane, William Chan","submitted_at":"2019-06-13T23:52:16Z","abstract_excerpt":"Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping speech with similar frequency and temporal characteristics. We propose the use of speaker-targeted acoustic and audio-visual models for this task. We complement the acoustic features in a hybrid DNN-HMM model with information of the target speaker's identity as well as visual features from the mouth region of the target speaker. Experimentation was p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05962","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":"2026-05-17T23:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DErH6K2DqOuFIiZBzQNHBEe3qxws+BJ5iK/nnLjPq3OhnNFP755Gy2gfVKC5zdVVErm6Oaiww/Y1598iOgqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:48:55.684210Z"},"content_sha256":"ba20a278505478b17ef947315c555149e8c118bf1958cab6ac7860868126d233","schema_version":"1.0","event_id":"sha256:ba20a278505478b17ef947315c555149e8c118bf1958cab6ac7860868126d233"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE/bundle.json","state_url":"https://pith.science/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE/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":"2026-05-28T21:48:55Z","links":{"resolver":"https://pith.science/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE","bundle":"https://pith.science/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE/bundle.json","state":"https://pith.science/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7L5A6KMTNHVFGJA4X4WM6X4TIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7L5A6KMTNHVFGJA4X4WM6X4TIE","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":"de107fba9a224018bbfc683dacbdb7b9a2b9216f83c2343a118f064ab23cfa0f","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-13T23:52:16Z","title_canon_sha256":"3185457c1a11a94879e2b58538ac1573240b2f2625f36e0e3a0663026eaaf103"},"schema_version":"1.0","source":{"id":"1906.05962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05962","created_at":"2026-05-17T23:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05962v1","created_at":"2026-05-17T23:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05962","created_at":"2026-05-17T23:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"7L5A6KMTNHVF","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7L5A6KMTNHVFGJA4","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7L5A6KMT","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:ba20a278505478b17ef947315c555149e8c118bf1958cab6ac7860868126d233","target":"graph","created_at":"2026-05-17T23:43:20Z","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":"Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping speech with similar frequency and temporal characteristics. We propose the use of speaker-targeted acoustic and audio-visual models for this task. We complement the acoustic features in a hybrid DNN-HMM model with information of the target speaker's identity as well as visual features from the mouth region of the target speaker. Experimentation was p","authors_text":"Guan-Lin Chao, Ian Lane, William Chan","cross_cats":["cs.CL","cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-13T23:52:16Z","title":"Speaker-Targeted Audio-Visual Models for Speech Recognition in Cocktail-Party Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05962","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":"sha256:182434b994a8648db814c0abe34285ffa977155941e912565818d4a55d0e8781","target":"record","created_at":"2026-05-17T23:43:20Z","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":"de107fba9a224018bbfc683dacbdb7b9a2b9216f83c2343a118f064ab23cfa0f","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-13T23:52:16Z","title_canon_sha256":"3185457c1a11a94879e2b58538ac1573240b2f2625f36e0e3a0663026eaaf103"},"schema_version":"1.0","source":{"id":"1906.05962","kind":"arxiv","version":1}},"canonical_sha256":"fafa0f299369ea53241cbf2ccf5f934125e367f36d9048b6085d461de74f3df2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fafa0f299369ea53241cbf2ccf5f934125e367f36d9048b6085d461de74f3df2","first_computed_at":"2026-05-17T23:43:20.177792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:20.177792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"so8XQpoQNXuC+eyOFU+caAYhRjhgPfivXPBFLGVeH43eYyla/GZLzgMPmZ0VQU1LiD3MCXvR8KMmvn/UNJ1jAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:20.178397Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:182434b994a8648db814c0abe34285ffa977155941e912565818d4a55d0e8781","sha256:ba20a278505478b17ef947315c555149e8c118bf1958cab6ac7860868126d233"],"state_sha256":"9f405a28fd7af820f8771f7f0ff015d464628cee796aba35df8f1e753140f078"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R3lqKNoed83GUltkhnrwAfbUENfYBsuo8gwLEv0rrDFuc6p8RtwBPwdgMR4gnOfhxkP+Sybcgr73+KHgtYBuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:48:55.688023Z","bundle_sha256":"690585fca73fd6d4809d38d0ed342d5a926f8b76455ad06bd2eaf4f45326e3e6"}}