{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MOWGGZCUUKGKJCDIJD7FQTIQYY","short_pith_number":"pith:MOWGGZCU","canonical_record":{"source":{"id":"1703.06284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-18T10:59:03Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9c1027cf8cdaa7ec88aadc8a46f0be7d663d28a6e77cf55912b549401feb06e4","abstract_canon_sha256":"a8b986ab225af81b5debe884cc2a2333d0902353d6c8b5fdc7d629919b9aa87e"},"schema_version":"1.0"},"canonical_sha256":"63ac636454a28ca4886848fe584d10c62ab8e357d583e0396a59f01029e5b77f","source":{"kind":"arxiv","id":"1703.06284","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06284","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06284v2","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06284","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"MOWGGZCUUKGK","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MOWGGZCUUKGKJCDI","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MOWGGZCU","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MOWGGZCUUKGKJCDIJD7FQTIQYY","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-18T10:59:03Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"9c1027cf8cdaa7ec88aadc8a46f0be7d663d28a6e77cf55912b549401feb06e4","abstract_canon_sha256":"a8b986ab225af81b5debe884cc2a2333d0902353d6c8b5fdc7d629919b9aa87e"},"schema_version":"1.0"},"canonical_sha256":"63ac636454a28ca4886848fe584d10c62ab8e357d583e0396a59f01029e5b77f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:03.787677Z","signature_b64":"DBeKtLYgpsIhZRaAFzfbYgozrFkEjak8+HGNacM3vcjeP+FQGYIO2AEzMfPPYdxCPlL9WzM3kHa61RxPoIRTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63ac636454a28ca4886848fe584d10c62ab8e357d583e0396a59f01029e5b77f","last_reissued_at":"2026-05-17T23:59:03.786964Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:03.786964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06284","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NaUOSCbKnAIdzSds+GqIYNAo1ZM/eGtt4tM7ZPIZjfq6zePXL/u12xwCLP4CIdI7dN0+wPnpUR58qna5GeyqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:38:33.777117Z"},"content_sha256":"a86c08e0fd130ed5ce5807c5af8f6cf65739a6de2ad275c73cb4a2bec8455553","schema_version":"1.0","event_id":"sha256:a86c08e0fd130ed5ce5807c5af8f6cf65739a6de2ad275c73cb4a2bec8455553"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MOWGGZCUUKGKJCDIJD7FQTIQYY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dong Yu, Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","submitted_at":"2017-03-18T10:59:03Z","abstract_excerpt":"In this paper we propose the utterance-level Permutation Invariant Training (uPIT) technique. uPIT is a practically applicable, end-to-end, deep learning based solution for speaker independent multi-talker speech separation. Specifically, uPIT extends the recently proposed Permutation Invariant Training (PIT) technique with an utterance-level cost function, hence eliminating the need for solving an additional permutation problem during inference, which is otherwise required by frame-level PIT. We achieve this using Recurrent Neural Networks (RNNs) that, during training, minimize the utterance-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06284","kind":"arxiv","version":2},"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":"2026-05-17T23:59:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EphfjSo9IpiaRbxxjEhxorItbeEEKNhIhdw5WesIXtkLNmtjvoAlxCG3yWWm8PFwAebkHpucFdYfKh+UkkJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:38:33.777526Z"},"content_sha256":"20a527550a9457c96db3893261330b4175475accabd0ad0a579812603b758806","schema_version":"1.0","event_id":"sha256:20a527550a9457c96db3893261330b4175475accabd0ad0a579812603b758806"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY/bundle.json","state_url":"https://pith.science/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY/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":"2026-06-06T11:38:33Z","links":{"resolver":"https://pith.science/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY","bundle":"https://pith.science/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY/bundle.json","state":"https://pith.science/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOWGGZCUUKGKJCDIJD7FQTIQYY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MOWGGZCUUKGKJCDIJD7FQTIQYY","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":"a8b986ab225af81b5debe884cc2a2333d0902353d6c8b5fdc7d629919b9aa87e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-18T10:59:03Z","title_canon_sha256":"9c1027cf8cdaa7ec88aadc8a46f0be7d663d28a6e77cf55912b549401feb06e4"},"schema_version":"1.0","source":{"id":"1703.06284","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06284","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06284v2","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06284","created_at":"2026-05-17T23:59:03Z"},{"alias_kind":"pith_short_12","alias_value":"MOWGGZCUUKGK","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MOWGGZCUUKGKJCDI","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MOWGGZCU","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:20a527550a9457c96db3893261330b4175475accabd0ad0a579812603b758806","target":"graph","created_at":"2026-05-17T23:59:03Z","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 propose the utterance-level Permutation Invariant Training (uPIT) technique. uPIT is a practically applicable, end-to-end, deep learning based solution for speaker independent multi-talker speech separation. Specifically, uPIT extends the recently proposed Permutation Invariant Training (PIT) technique with an utterance-level cost function, hence eliminating the need for solving an additional permutation problem during inference, which is otherwise required by frame-level PIT. We achieve this using Recurrent Neural Networks (RNNs) that, during training, minimize the utterance-","authors_text":"Dong Yu, Jesper Jensen, Morten Kolb{\\ae}k, Zheng-Hua Tan","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-18T10:59:03Z","title":"Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06284","kind":"arxiv","version":2},"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:a86c08e0fd130ed5ce5807c5af8f6cf65739a6de2ad275c73cb4a2bec8455553","target":"record","created_at":"2026-05-17T23:59:03Z","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":"a8b986ab225af81b5debe884cc2a2333d0902353d6c8b5fdc7d629919b9aa87e","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-03-18T10:59:03Z","title_canon_sha256":"9c1027cf8cdaa7ec88aadc8a46f0be7d663d28a6e77cf55912b549401feb06e4"},"schema_version":"1.0","source":{"id":"1703.06284","kind":"arxiv","version":2}},"canonical_sha256":"63ac636454a28ca4886848fe584d10c62ab8e357d583e0396a59f01029e5b77f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63ac636454a28ca4886848fe584d10c62ab8e357d583e0396a59f01029e5b77f","first_computed_at":"2026-05-17T23:59:03.786964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:03.786964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DBeKtLYgpsIhZRaAFzfbYgozrFkEjak8+HGNacM3vcjeP+FQGYIO2AEzMfPPYdxCPlL9WzM3kHa61RxPoIRTCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:03.787677Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06284","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a86c08e0fd130ed5ce5807c5af8f6cf65739a6de2ad275c73cb4a2bec8455553","sha256:20a527550a9457c96db3893261330b4175475accabd0ad0a579812603b758806"],"state_sha256":"3017b790ebf8e6b2277077155bcfbd2a5fa2c94f91798e1794edc90d97363e42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnXwVuQ3quWTdgQi9bfFA8q2RS3BUuR7XaFgie2NH+g+KIUbY2zm0/kXEioofEy0Bux8O9BWH6SrJQbe/C/cDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:38:33.780424Z","bundle_sha256":"f84f37191d72d8b2067f0385ab72e06b8ac063190dded28bde8a4027ef625c75"}}