{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:V4R7BKEAYKXJW5UGF6NSOWATWB","short_pith_number":"pith:V4R7BKEA","canonical_record":{"source":{"id":"1907.04462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T23:53:39Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"89e029f57f66cb9a6daf953f739d9c1c70df7afc91af6f2f67eecee4da6abca6","abstract_canon_sha256":"8c9b8747af34a1c5af483d4d105565916e1fb454112859db07fa66ce9c52daaf"},"schema_version":"1.0"},"canonical_sha256":"af23f0a880c2ae9b76862f9b275813b055c347b62e544a7d215292ec6abe4655","source":{"kind":"arxiv","id":"1907.04462","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04462","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04462v1","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04462","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"V4R7BKEAYKXJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"V4R7BKEAYKXJW5UG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"V4R7BKEA","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:V4R7BKEAYKXJW5UGF6NSOWATWB","target":"record","payload":{"canonical_record":{"source":{"id":"1907.04462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T23:53:39Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"89e029f57f66cb9a6daf953f739d9c1c70df7afc91af6f2f67eecee4da6abca6","abstract_canon_sha256":"8c9b8747af34a1c5af483d4d105565916e1fb454112859db07fa66ce9c52daaf"},"schema_version":"1.0"},"canonical_sha256":"af23f0a880c2ae9b76862f9b275813b055c347b62e544a7d215292ec6abe4655","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:00.226850Z","signature_b64":"yOO6dHLFar7x6zFjieSie8giXdAowWOB3u3Dt+gQcb84QG04XgZ8sYINTqjmG7ABgy6UymXYbGCrT2Oof5ljCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af23f0a880c2ae9b76862f9b275813b055c347b62e544a7d215292ec6abe4655","last_reissued_at":"2026-05-17T23:41:00.226215Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:00.226215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.04462","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":"2026-05-17T23:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B/StMxP9NUaUkyBphcrUrxvUSFeFUZ/rVOK70cTkhZxq9E75+LsuYlbmyJKMRCIi7kb8yXofQBTPUemHZpLvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:17:48.430633Z"},"content_sha256":"3a1f635c4922369205db73f20257f9d83bf26127adb57c338b492b3962d78c35","schema_version":"1.0","event_id":"sha256:3a1f635c4922369205db73f20257f9d83bf26127adb57c338b492b3962d78c35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:V4R7BKEAYKXJW5UGF6NSOWATWB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Speaker End-to-End 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":"Jihyun Park, Kainan Peng, Kexin Zhao, Wei Ping","submitted_at":"2019-07-09T23:53:39Z","abstract_excerpt":"In this work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of different voices, low dimensional trainable speaker embeddings are shared across each component of ClariNet and trained together with the rest of the model. We demonstrate that the multi-speaker ClariNet outperforms state-of-the-art systems in terms of naturalness, because the whole model is jointly optimized in an end-to-end manner."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04462","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":"2026-05-17T23:41:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1rCQTgcMHjzYGgC1fAdi4SCQFloB+kgSofTxv2JbtVIPANoqRpnq+B468HSmwbn5WLOM6JsgsFO1eLFMgBMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:17:48.431350Z"},"content_sha256":"cbc14c64c26ed5b305dea74347a6998ac6dbb457ac7a1bc4db403c0ae27356a9","schema_version":"1.0","event_id":"sha256:cbc14c64c26ed5b305dea74347a6998ac6dbb457ac7a1bc4db403c0ae27356a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4R7BKEAYKXJW5UGF6NSOWATWB/bundle.json","state_url":"https://pith.science/pith/V4R7BKEAYKXJW5UGF6NSOWATWB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4R7BKEAYKXJW5UGF6NSOWATWB/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":"2026-05-25T21:17:48Z","links":{"resolver":"https://pith.science/pith/V4R7BKEAYKXJW5UGF6NSOWATWB","bundle":"https://pith.science/pith/V4R7BKEAYKXJW5UGF6NSOWATWB/bundle.json","state":"https://pith.science/pith/V4R7BKEAYKXJW5UGF6NSOWATWB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4R7BKEAYKXJW5UGF6NSOWATWB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:V4R7BKEAYKXJW5UGF6NSOWATWB","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":"8c9b8747af34a1c5af483d4d105565916e1fb454112859db07fa66ce9c52daaf","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T23:53:39Z","title_canon_sha256":"89e029f57f66cb9a6daf953f739d9c1c70df7afc91af6f2f67eecee4da6abca6"},"schema_version":"1.0","source":{"id":"1907.04462","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.04462","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"arxiv_version","alias_value":"1907.04462v1","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.04462","created_at":"2026-05-17T23:41:00Z"},{"alias_kind":"pith_short_12","alias_value":"V4R7BKEAYKXJ","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"V4R7BKEAYKXJW5UG","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"V4R7BKEA","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:cbc14c64c26ed5b305dea74347a6998ac6dbb457ac7a1bc4db403c0ae27356a9","target":"graph","created_at":"2026-05-17T23:41:00Z","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 work, we extend ClariNet (Ping et al., 2019), a fully end-to-end speech synthesis model (i.e., text-to-wave), to generate high-fidelity speech from multiple speakers. To model the unique characteristic of different voices, low dimensional trainable speaker embeddings are shared across each component of ClariNet and trained together with the rest of the model. We demonstrate that the multi-speaker ClariNet outperforms state-of-the-art systems in terms of naturalness, because the whole model is jointly optimized in an end-to-end manner.","authors_text":"Jihyun Park, Kainan Peng, Kexin Zhao, Wei Ping","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T23:53:39Z","title":"Multi-Speaker End-to-End Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.04462","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":"sha256:3a1f635c4922369205db73f20257f9d83bf26127adb57c338b492b3962d78c35","target":"record","created_at":"2026-05-17T23:41:00Z","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":"8c9b8747af34a1c5af483d4d105565916e1fb454112859db07fa66ce9c52daaf","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-09T23:53:39Z","title_canon_sha256":"89e029f57f66cb9a6daf953f739d9c1c70df7afc91af6f2f67eecee4da6abca6"},"schema_version":"1.0","source":{"id":"1907.04462","kind":"arxiv","version":1}},"canonical_sha256":"af23f0a880c2ae9b76862f9b275813b055c347b62e544a7d215292ec6abe4655","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af23f0a880c2ae9b76862f9b275813b055c347b62e544a7d215292ec6abe4655","first_computed_at":"2026-05-17T23:41:00.226215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:00.226215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yOO6dHLFar7x6zFjieSie8giXdAowWOB3u3Dt+gQcb84QG04XgZ8sYINTqjmG7ABgy6UymXYbGCrT2Oof5ljCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:00.226850Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.04462","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a1f635c4922369205db73f20257f9d83bf26127adb57c338b492b3962d78c35","sha256:cbc14c64c26ed5b305dea74347a6998ac6dbb457ac7a1bc4db403c0ae27356a9"],"state_sha256":"8bfda7b43bf66a69132e2698451d9e19edacd46ea68faa1d275adcf0090133f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UCneXTD52FXNkl+84/cU0Gyw4Vhm8iKV/uCxbz5SW6ht18QXQQ9Ak4k/RDfcA2nyuR2sUNsMOu97VdzCm2LWCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:17:48.435214Z","bundle_sha256":"7cc09ec31d6712526687439c77b43f92f56766a54d801b25c2e3cd5a22613d61"}}