{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WCJAGKPZ64B7NGWZUXRRPSE4GZ","short_pith_number":"pith:WCJAGKPZ","canonical_record":{"source":{"id":"1806.04558","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-12T14:29:22Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"9e4cac955ad37a1225a5cfc2f4ab03b493659187839ce76b5c09eea060ff3137","abstract_canon_sha256":"38b5228479e80a2ee2e666b1ffb9bd1295a1d40aa847004e072562ba989bc8fd"},"schema_version":"1.0"},"canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","source":{"kind":"arxiv","id":"1806.04558","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04558","created_at":"2026-05-17T23:57:02Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04558v4","created_at":"2026-05-17T23:57:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04558","created_at":"2026-05-17T23:57:02Z"},{"alias_kind":"pith_short_12","alias_value":"WCJAGKPZ64B7","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WCJAGKPZ64B7NGWZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WCJAGKPZ","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WCJAGKPZ64B7NGWZUXRRPSE4GZ","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04558","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-12T14:29:22Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"9e4cac955ad37a1225a5cfc2f4ab03b493659187839ce76b5c09eea060ff3137","abstract_canon_sha256":"38b5228479e80a2ee2e666b1ffb9bd1295a1d40aa847004e072562ba989bc8fd"},"schema_version":"1.0"},"canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:02.884173Z","signature_b64":"cXr/UrCO5mYJXMcH5efZ77j7qqMDRSF493SCYcwcPOAjDgtgTWiY6oHzKMpiA3He0JfoW0yenkTlBPiGUBmRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","last_reissued_at":"2026-05-17T23:57:02.883524Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:02.883524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04558","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OyFkXiGQdgxaJNr4q6f1pQ4w0ueMwq7+w5lEIGhjLjUrrSTYtadS3KuDXCbDiuvy96EW6RIpkT5w7bYr1htPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:47:03.528289Z"},"content_sha256":"ba98790050d0537e6c04f6f47f01a41f573f5a4006bf88e1244479ac214a8900","schema_version":"1.0","event_id":"sha256:ba98790050d0537e6c04f6f47f01a41f573f5a4006bf88e1244479ac214a8900"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WCJAGKPZ64B7NGWZUXRRPSE4GZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Fei Ren, Ignacio Lopez Moreno, Jonathan Shen, Patrick Nguyen, Quan Wang, Ron J. Weiss, Ruoming Pang, Ye Jia, Yonghui Wu, Yu Zhang, Zhifeng Chen","submitted_at":"2018-06-12T14:29:22Z","abstract_excerpt":"We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04558","kind":"arxiv","version":4},"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":"2026-05-17T23:57:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/iR8zKFYa2O1pl8wCPqraDPnYk72nZCXdSb8NeYAt8jpCtcTvaoDeOfT0I7gxMKj4DmMpjlXMerKaiqXecO0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T13:47:03.529024Z"},"content_sha256":"42637e3057a32c8ef4aabb0c6060e2d981affc7e79dedaee346b67a53d3eeb73","schema_version":"1.0","event_id":"sha256:42637e3057a32c8ef4aabb0c6060e2d981affc7e79dedaee346b67a53d3eeb73"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/bundle.json","state_url":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/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":"2026-05-25T13:47:03Z","links":{"resolver":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ","bundle":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/bundle.json","state":"https://pith.science/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCJAGKPZ64B7NGWZUXRRPSE4GZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WCJAGKPZ64B7NGWZUXRRPSE4GZ","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":"38b5228479e80a2ee2e666b1ffb9bd1295a1d40aa847004e072562ba989bc8fd","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-12T14:29:22Z","title_canon_sha256":"9e4cac955ad37a1225a5cfc2f4ab03b493659187839ce76b5c09eea060ff3137"},"schema_version":"1.0","source":{"id":"1806.04558","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04558","created_at":"2026-05-17T23:57:02Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04558v4","created_at":"2026-05-17T23:57:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04558","created_at":"2026-05-17T23:57:02Z"},{"alias_kind":"pith_short_12","alias_value":"WCJAGKPZ64B7","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WCJAGKPZ64B7NGWZ","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WCJAGKPZ","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:42637e3057a32c8ef4aabb0c6060e2d981affc7e79dedaee346b67a53d3eeb73","target":"graph","created_at":"2026-05-17T23:57:02Z","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":"We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which g","authors_text":"Fei Ren, Ignacio Lopez Moreno, Jonathan Shen, Patrick Nguyen, Quan Wang, Ron J. Weiss, Ruoming Pang, Ye Jia, Yonghui Wu, Yu Zhang, Zhifeng Chen","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-12T14:29:22Z","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04558","kind":"arxiv","version":4},"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:ba98790050d0537e6c04f6f47f01a41f573f5a4006bf88e1244479ac214a8900","target":"record","created_at":"2026-05-17T23:57:02Z","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":"38b5228479e80a2ee2e666b1ffb9bd1295a1d40aa847004e072562ba989bc8fd","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-12T14:29:22Z","title_canon_sha256":"9e4cac955ad37a1225a5cfc2f4ab03b493659187839ce76b5c09eea060ff3137"},"schema_version":"1.0","source":{"id":"1806.04558","kind":"arxiv","version":4}},"canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0920329f9f703f69ad9a5e317c89c3646433b6e07e296c38d109d61bd2e5b7c","first_computed_at":"2026-05-17T23:57:02.883524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:02.883524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cXr/UrCO5mYJXMcH5efZ77j7qqMDRSF493SCYcwcPOAjDgtgTWiY6oHzKMpiA3He0JfoW0yenkTlBPiGUBmRDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:02.884173Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04558","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba98790050d0537e6c04f6f47f01a41f573f5a4006bf88e1244479ac214a8900","sha256:42637e3057a32c8ef4aabb0c6060e2d981affc7e79dedaee346b67a53d3eeb73"],"state_sha256":"afcfb5e81d313f3bde34bcd8591bf7c956211eec53a761c99e5480759c85b3ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGG0tfZkuZwje1g7Z1BqpthP/Ye3OjzCzObhpJK3n0rCfrwRL49nUmOcc++//7rR3/miCJ1COn4bAMBuaLBBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T13:47:03.532894Z","bundle_sha256":"63aa73c73eb6329652354f025364b60eed9124f28e543ec5461b05f79010eaa8"}}