{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:NRIAZH7JJWOY62SW4CVXT722V3","short_pith_number":"pith:NRIAZH7J","canonical_record":{"source":{"id":"1810.04826","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-11T02:57:14Z","cross_cats_sorted":["cs.LG","eess.SP","stat.ML"],"title_canon_sha256":"817e02dab9d4400a9c6b34a2796128a751523526f31eaeea54e0694af023b34f","abstract_canon_sha256":"33200deb75ddcc37525fdeb95c688a27bb3854e18f73b40e6b9c3e23d2291971"},"schema_version":"1.0"},"canonical_sha256":"6c500c9fe94d9d8f6a56e0ab79ff5aaeda94793aacce5bddae0c648af44e4ccc","source":{"kind":"arxiv","id":"1810.04826","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04826","created_at":"2026-05-17T23:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04826v6","created_at":"2026-05-17T23:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04826","created_at":"2026-05-17T23:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"NRIAZH7JJWOY","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NRIAZH7JJWOY62SW","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NRIAZH7J","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:NRIAZH7JJWOY62SW4CVXT722V3","target":"record","payload":{"canonical_record":{"source":{"id":"1810.04826","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-11T02:57:14Z","cross_cats_sorted":["cs.LG","eess.SP","stat.ML"],"title_canon_sha256":"817e02dab9d4400a9c6b34a2796128a751523526f31eaeea54e0694af023b34f","abstract_canon_sha256":"33200deb75ddcc37525fdeb95c688a27bb3854e18f73b40e6b9c3e23d2291971"},"schema_version":"1.0"},"canonical_sha256":"6c500c9fe94d9d8f6a56e0ab79ff5aaeda94793aacce5bddae0c648af44e4ccc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:58.774438Z","signature_b64":"2GgIfDzEuZPYu+bW7+ny3xbdXMnAy0KGSmOK/rNyzRKYBc8MVZg9fwhUibYr+YjG1Q9AH/20011z0F4ow5DdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c500c9fe94d9d8f6a56e0ab79ff5aaeda94793aacce5bddae0c648af44e4ccc","last_reissued_at":"2026-05-17T23:42:58.774006Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:58.774006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.04826","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pIe8KWn1qH2kOrpA06olHlYunj4WyIGxSJ9Yk4L//f/7WxIW/QsqvUmfVMsTrEWVBf8IaL+ISqu/khYeKqoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T04:10:49.628640Z"},"content_sha256":"5eaf97b12c212afb40ea482991fac70d2ae369a18f2dcbdd8366cf08c7c8158e","schema_version":"1.0","event_id":"sha256:5eaf97b12c212afb40ea482991fac70d2ae369a18f2dcbdd8366cf08c7c8158e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:NRIAZH7JJWOY62SW4CVXT722V3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hannah Muckenhirn, Ignacio Lopez Moreno, John Hershey, Kevin Wilson, Prashant Sridhar, Quan Wang, Rif A. Saurous, Ron J. Weiss, Ye Jia, Zelin Wu","submitted_at":"2018-10-11T02:57:14Z","abstract_excerpt":"In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask. Our system significantly reduces the speech recognition WER on multi-speaker signals, with minimal WER degradation on single-speaker signals."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04826","kind":"arxiv","version":6},"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":"2026-05-17T23:42:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6/1gh+/k2nec7cX544wJmtne19ywW8o3F1lHiKR0g5kEOeAPU8lqiVzipPtgP4Y9r6jgtYGjBpLjMQHonyNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T04:10:49.629352Z"},"content_sha256":"b569a76f6f3b5727d902f133b45da335d57c0c70ed48ceae0ce296b113083da7","schema_version":"1.0","event_id":"sha256:b569a76f6f3b5727d902f133b45da335d57c0c70ed48ceae0ce296b113083da7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRIAZH7JJWOY62SW4CVXT722V3/bundle.json","state_url":"https://pith.science/pith/NRIAZH7JJWOY62SW4CVXT722V3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRIAZH7JJWOY62SW4CVXT722V3/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":"2026-05-23T04:10:49Z","links":{"resolver":"https://pith.science/pith/NRIAZH7JJWOY62SW4CVXT722V3","bundle":"https://pith.science/pith/NRIAZH7JJWOY62SW4CVXT722V3/bundle.json","state":"https://pith.science/pith/NRIAZH7JJWOY62SW4CVXT722V3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRIAZH7JJWOY62SW4CVXT722V3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:NRIAZH7JJWOY62SW4CVXT722V3","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":"33200deb75ddcc37525fdeb95c688a27bb3854e18f73b40e6b9c3e23d2291971","cross_cats_sorted":["cs.LG","eess.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-11T02:57:14Z","title_canon_sha256":"817e02dab9d4400a9c6b34a2796128a751523526f31eaeea54e0694af023b34f"},"schema_version":"1.0","source":{"id":"1810.04826","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.04826","created_at":"2026-05-17T23:42:58Z"},{"alias_kind":"arxiv_version","alias_value":"1810.04826v6","created_at":"2026-05-17T23:42:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04826","created_at":"2026-05-17T23:42:58Z"},{"alias_kind":"pith_short_12","alias_value":"NRIAZH7JJWOY","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"NRIAZH7JJWOY62SW","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"NRIAZH7J","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:b569a76f6f3b5727d902f133b45da335d57c0c70ed48ceae0ce296b113083da7","target":"graph","created_at":"2026-05-17T23:42:58Z","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 a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask. Our system significantly reduces the speech recognition WER on multi-speaker signals, with minimal WER degradation on single-speaker signals.","authors_text":"Hannah Muckenhirn, Ignacio Lopez Moreno, John Hershey, Kevin Wilson, Prashant Sridhar, Quan Wang, Rif A. Saurous, Ron J. Weiss, Ye Jia, Zelin Wu","cross_cats":["cs.LG","eess.SP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-11T02:57:14Z","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04826","kind":"arxiv","version":6},"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":"sha256:5eaf97b12c212afb40ea482991fac70d2ae369a18f2dcbdd8366cf08c7c8158e","target":"record","created_at":"2026-05-17T23:42:58Z","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":"33200deb75ddcc37525fdeb95c688a27bb3854e18f73b40e6b9c3e23d2291971","cross_cats_sorted":["cs.LG","eess.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-11T02:57:14Z","title_canon_sha256":"817e02dab9d4400a9c6b34a2796128a751523526f31eaeea54e0694af023b34f"},"schema_version":"1.0","source":{"id":"1810.04826","kind":"arxiv","version":6}},"canonical_sha256":"6c500c9fe94d9d8f6a56e0ab79ff5aaeda94793aacce5bddae0c648af44e4ccc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c500c9fe94d9d8f6a56e0ab79ff5aaeda94793aacce5bddae0c648af44e4ccc","first_computed_at":"2026-05-17T23:42:58.774006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:58.774006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2GgIfDzEuZPYu+bW7+ny3xbdXMnAy0KGSmOK/rNyzRKYBc8MVZg9fwhUibYr+YjG1Q9AH/20011z0F4ow5DdBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:58.774438Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.04826","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5eaf97b12c212afb40ea482991fac70d2ae369a18f2dcbdd8366cf08c7c8158e","sha256:b569a76f6f3b5727d902f133b45da335d57c0c70ed48ceae0ce296b113083da7"],"state_sha256":"60c19f1e0503b7afdf034520500e3d866e9ac529400227a79695aeb855b7eed9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"10gjlM9X7xxvgTuRb7VqTpjL2fN9m8e7pX7K7vOIBtnLCqBArljXGQ0p4QGyxSnHYm5IGG+c2s1RF4Q6gWTmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T04:10:49.633386Z","bundle_sha256":"1e934fe3be12b9475013bd274c5aaf2d9e5e79221cf95496450770e4d8e6a314"}}