{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HCA3UV3IQCOQQUJOGJAWX3OWLW","short_pith_number":"pith:HCA3UV3I","canonical_record":{"source":{"id":"1803.09017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-23T23:56:49Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b7597da181cfab8487836f5c2dbe7a0458a79b92464d95f87ef971c14c68f78d","abstract_canon_sha256":"d727b795001c6ddb23471cc4cdb79dc01542d0164bda1c0ee10a9d834cfe4e42"},"schema_version":"1.0"},"canonical_sha256":"3881ba5768809d08512e32416bedd65d99b36699ecc6be4353e95c36bd6d7de3","source":{"kind":"arxiv","id":"1803.09017","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09017","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09017v1","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09017","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"HCA3UV3IQCOQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HCA3UV3IQCOQQUJO","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HCA3UV3I","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HCA3UV3IQCOQQUJOGJAWX3OWLW","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09017","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-23T23:56:49Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b7597da181cfab8487836f5c2dbe7a0458a79b92464d95f87ef971c14c68f78d","abstract_canon_sha256":"d727b795001c6ddb23471cc4cdb79dc01542d0164bda1c0ee10a9d834cfe4e42"},"schema_version":"1.0"},"canonical_sha256":"3881ba5768809d08512e32416bedd65d99b36699ecc6be4353e95c36bd6d7de3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:12.913427Z","signature_b64":"8N2YrDZfpktAM1Tb6+8Mmoe9/JY5afNJ9U/1XqvFGe+F/aAh6y/OJgDfDwl6icZHMG7K/OmcpY31792EqiLgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3881ba5768809d08512e32416bedd65d99b36699ecc6be4353e95c36bd6d7de3","last_reissued_at":"2026-05-18T00:20:12.912738Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:12.912738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09017","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":"2026-05-18T00:20:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v4xpBh4MKLj7/LW97ehyF/nO1JxMp5F11EpP7/ntEpq8Cuvnao8baphgLYK9r2J2wOV18rEqLW7a1Fqjag8oCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:03:23.881425Z"},"content_sha256":"5900f9a45719af20da96d8422ae6c7346be30683ec6f38646be14eeb82467af3","schema_version":"1.0","event_id":"sha256:5900f9a45719af20da96d8422ae6c7346be30683ec6f38646be14eeb82467af3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HCA3UV3IQCOQQUJOGJAWX3OWLW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in 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":"Daisy Stanton, Eric Battenberg, Fei Ren, Joel Shor, Rif A. Saurous, RJ Skerry-Ryan, Ye Jia, Ying Xiao, Yuxuan Wang, Yu Zhang","submitted_at":"2018-03-23T23:56:49Z","abstract_excerpt":"In this work, we propose \"global style tokens\" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to model a large range of acoustic expressiveness. GSTs lead to a rich set of significant results. The soft interpretable \"labels\" they generate can be used to control synthesis in novel ways, such as varying speed and speaking style - independently of the text content. They can also be used for style transfer, replicating the speaking style of a single audio cli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09017","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":"2026-05-18T00:20:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FcvQqJU3fATIEcyU65sQK2eRtsh+BOJnIK0UqAHUntbT9Aq2+gnLvRed+o8qvxhz1zPUc2p9JriRvzl1n4PNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T05:03:23.882073Z"},"content_sha256":"2cfdf9c9efd13799b475df499c4bc49993ffb715732eed2447dcd23df490fbd7","schema_version":"1.0","event_id":"sha256:2cfdf9c9efd13799b475df499c4bc49993ffb715732eed2447dcd23df490fbd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW/bundle.json","state_url":"https://pith.science/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW/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":"2026-06-08T05:03:23Z","links":{"resolver":"https://pith.science/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW","bundle":"https://pith.science/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW/bundle.json","state":"https://pith.science/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCA3UV3IQCOQQUJOGJAWX3OWLW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HCA3UV3IQCOQQUJOGJAWX3OWLW","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":"d727b795001c6ddb23471cc4cdb79dc01542d0164bda1c0ee10a9d834cfe4e42","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-23T23:56:49Z","title_canon_sha256":"b7597da181cfab8487836f5c2dbe7a0458a79b92464d95f87ef971c14c68f78d"},"schema_version":"1.0","source":{"id":"1803.09017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09017","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09017v1","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09017","created_at":"2026-05-18T00:20:12Z"},{"alias_kind":"pith_short_12","alias_value":"HCA3UV3IQCOQ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HCA3UV3IQCOQQUJO","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HCA3UV3I","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:2cfdf9c9efd13799b475df499c4bc49993ffb715732eed2447dcd23df490fbd7","target":"graph","created_at":"2026-05-18T00:20:12Z","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 propose \"global style tokens\" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to model a large range of acoustic expressiveness. GSTs lead to a rich set of significant results. The soft interpretable \"labels\" they generate can be used to control synthesis in novel ways, such as varying speed and speaking style - independently of the text content. They can also be used for style transfer, replicating the speaking style of a single audio cli","authors_text":"Daisy Stanton, Eric Battenberg, Fei Ren, Joel Shor, Rif A. Saurous, RJ Skerry-Ryan, Ye Jia, Ying Xiao, Yuxuan Wang, Yu Zhang","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-23T23:56:49Z","title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09017","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":"sha256:5900f9a45719af20da96d8422ae6c7346be30683ec6f38646be14eeb82467af3","target":"record","created_at":"2026-05-18T00:20:12Z","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":"d727b795001c6ddb23471cc4cdb79dc01542d0164bda1c0ee10a9d834cfe4e42","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-23T23:56:49Z","title_canon_sha256":"b7597da181cfab8487836f5c2dbe7a0458a79b92464d95f87ef971c14c68f78d"},"schema_version":"1.0","source":{"id":"1803.09017","kind":"arxiv","version":1}},"canonical_sha256":"3881ba5768809d08512e32416bedd65d99b36699ecc6be4353e95c36bd6d7de3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3881ba5768809d08512e32416bedd65d99b36699ecc6be4353e95c36bd6d7de3","first_computed_at":"2026-05-18T00:20:12.912738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:12.912738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8N2YrDZfpktAM1Tb6+8Mmoe9/JY5afNJ9U/1XqvFGe+F/aAh6y/OJgDfDwl6icZHMG7K/OmcpY31792EqiLgDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:12.913427Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5900f9a45719af20da96d8422ae6c7346be30683ec6f38646be14eeb82467af3","sha256:2cfdf9c9efd13799b475df499c4bc49993ffb715732eed2447dcd23df490fbd7"],"state_sha256":"fc1a683f0c608b12c6ed6139b091580740d07d937f2729cc4a066b9212b4be51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZq033bpvwbSHCH6KENn5tdEy3i4GfNiLA4U5/KjfD+k0gtGZ2iKwhAwcNzAiYegcfPhCLRiRPcnOxNa5LmJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T05:03:23.885607Z","bundle_sha256":"5de268e22a446c3ccbb0ece0a2546784b30c4fdfce254846802916930fd51318"}}