{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PG7SA7T3BFMFBB3APNLFPSUG6A","short_pith_number":"pith:PG7SA7T3","canonical_record":{"source":{"id":"1711.00520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-01T19:40:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"cc01644fb7110e434cd38b2fbcf54ab12ac495b5f32d5416265451ebe01c21a5","abstract_canon_sha256":"1017390fc44166cbe47dd5670c04526f54491fb91ad8907277e2795f30bcbfe2"},"schema_version":"1.0"},"canonical_sha256":"79bf207e7b09585087607b5657ca86f03ee80215ca0ee311ceb0fd09a81fa6ee","source":{"kind":"arxiv","id":"1711.00520","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00520","created_at":"2026-05-18T00:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00520v1","created_at":"2026-05-18T00:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00520","created_at":"2026-05-18T00:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"PG7SA7T3BFMF","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PG7SA7T3BFMFBB3A","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PG7SA7T3","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PG7SA7T3BFMFBB3APNLFPSUG6A","target":"record","payload":{"canonical_record":{"source":{"id":"1711.00520","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-01T19:40:00Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"cc01644fb7110e434cd38b2fbcf54ab12ac495b5f32d5416265451ebe01c21a5","abstract_canon_sha256":"1017390fc44166cbe47dd5670c04526f54491fb91ad8907277e2795f30bcbfe2"},"schema_version":"1.0"},"canonical_sha256":"79bf207e7b09585087607b5657ca86f03ee80215ca0ee311ceb0fd09a81fa6ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:30.381377Z","signature_b64":"cELYd5qej8/fHTbULoobQDCN3fje2xtMp+6K8LJOspDri8pyDk8va9PVQpLb3EfzjBUb0w71oMIioQ15yysYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79bf207e7b09585087607b5657ca86f03ee80215ca0ee311ceb0fd09a81fa6ee","last_reissued_at":"2026-05-18T00:31:30.380248Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:30.380248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.00520","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":"2026-05-18T00:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O9+BkplhWnfMWXD/5cdMkEikh9oXW2ByzMth7A4D3MLJCxNVP8TXFPrnfm9eHGY4CCbUMdDUJBGV+uHJKJX4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:00:47.146162Z"},"content_sha256":"02d4af64ce15e159a94d4f0114f62a871356238df6bfc6ea112dd836b52bf99b","schema_version":"1.0","event_id":"sha256:02d4af64ce15e159a94d4f0114f62a871356238df6bfc6ea112dd836b52bf99b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PG7SA7T3BFMFBB3APNLFPSUG6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncovering Latent Style Factors for Expressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CL","authors_text":"Daisy Stanton, Eric Battenberg, Joel Shor, Rif A. Saurous, RJ Skerry-Ryan, Rob Clark, Ying Xiao, Yuxuan Wang","submitted_at":"2017-11-01T19:40:00Z","abstract_excerpt":"Prosodic modeling is a core problem in speech synthesis. The key challenge is producing desirable prosody from textual input containing only phonetic information. In this preliminary study, we introduce the concept of \"style tokens\" in Tacotron, a recently proposed end-to-end neural speech synthesis model. Using style tokens, we aim to extract independent prosodic styles from training data. We show that without annotation data or an explicit supervision signal, our approach can automatically learn a variety of prosodic variations in a purely data-driven way. Importantly, each style token corre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00520","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":"2026-05-18T00:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4+NWLPgcCKGcOHOGAR+VCv7MdsohVBVcsbr46btXgsotkgc7wZhfFI++bOltR+QW0wk8wTau8NVKzOH/H+6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:00:47.146822Z"},"content_sha256":"8d313333d9fd1f7397c412ba5c7115b983c22f7675503fdab4af2ff1cde9b6b3","schema_version":"1.0","event_id":"sha256:8d313333d9fd1f7397c412ba5c7115b983c22f7675503fdab4af2ff1cde9b6b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PG7SA7T3BFMFBB3APNLFPSUG6A/bundle.json","state_url":"https://pith.science/pith/PG7SA7T3BFMFBB3APNLFPSUG6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PG7SA7T3BFMFBB3APNLFPSUG6A/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":"2026-05-25T21:00:47Z","links":{"resolver":"https://pith.science/pith/PG7SA7T3BFMFBB3APNLFPSUG6A","bundle":"https://pith.science/pith/PG7SA7T3BFMFBB3APNLFPSUG6A/bundle.json","state":"https://pith.science/pith/PG7SA7T3BFMFBB3APNLFPSUG6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PG7SA7T3BFMFBB3APNLFPSUG6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PG7SA7T3BFMFBB3APNLFPSUG6A","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":"1017390fc44166cbe47dd5670c04526f54491fb91ad8907277e2795f30bcbfe2","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-01T19:40:00Z","title_canon_sha256":"cc01644fb7110e434cd38b2fbcf54ab12ac495b5f32d5416265451ebe01c21a5"},"schema_version":"1.0","source":{"id":"1711.00520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.00520","created_at":"2026-05-18T00:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"1711.00520v1","created_at":"2026-05-18T00:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00520","created_at":"2026-05-18T00:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"PG7SA7T3BFMF","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PG7SA7T3BFMFBB3A","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PG7SA7T3","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:8d313333d9fd1f7397c412ba5c7115b983c22f7675503fdab4af2ff1cde9b6b3","target":"graph","created_at":"2026-05-18T00:31:30Z","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":"Prosodic modeling is a core problem in speech synthesis. The key challenge is producing desirable prosody from textual input containing only phonetic information. In this preliminary study, we introduce the concept of \"style tokens\" in Tacotron, a recently proposed end-to-end neural speech synthesis model. Using style tokens, we aim to extract independent prosodic styles from training data. We show that without annotation data or an explicit supervision signal, our approach can automatically learn a variety of prosodic variations in a purely data-driven way. Importantly, each style token corre","authors_text":"Daisy Stanton, Eric Battenberg, Joel Shor, Rif A. Saurous, RJ Skerry-Ryan, Rob Clark, Ying Xiao, Yuxuan Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-01T19:40:00Z","title":"Uncovering Latent Style Factors for Expressive Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00520","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":"sha256:02d4af64ce15e159a94d4f0114f62a871356238df6bfc6ea112dd836b52bf99b","target":"record","created_at":"2026-05-18T00:31:30Z","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":"1017390fc44166cbe47dd5670c04526f54491fb91ad8907277e2795f30bcbfe2","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-01T19:40:00Z","title_canon_sha256":"cc01644fb7110e434cd38b2fbcf54ab12ac495b5f32d5416265451ebe01c21a5"},"schema_version":"1.0","source":{"id":"1711.00520","kind":"arxiv","version":1}},"canonical_sha256":"79bf207e7b09585087607b5657ca86f03ee80215ca0ee311ceb0fd09a81fa6ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79bf207e7b09585087607b5657ca86f03ee80215ca0ee311ceb0fd09a81fa6ee","first_computed_at":"2026-05-18T00:31:30.380248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:30.380248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cELYd5qej8/fHTbULoobQDCN3fje2xtMp+6K8LJOspDri8pyDk8va9PVQpLb3EfzjBUb0w71oMIioQ15yysYAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:30.381377Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.00520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02d4af64ce15e159a94d4f0114f62a871356238df6bfc6ea112dd836b52bf99b","sha256:8d313333d9fd1f7397c412ba5c7115b983c22f7675503fdab4af2ff1cde9b6b3"],"state_sha256":"dabec21f1fb79eb7e956d9f964fd5f84aed79e36f5c73764fa6a2be01a3d5034"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3UtkgbpEbu5IgF55TexRp9Nx5K6y/v7XZXonEZoYsl759Ajb42q4zYH9AgMryPlvk9TXZYndP6mNS2t97ZACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:00:47.150586Z","bundle_sha256":"d6c466569adfefb95f420159b688fa4d9099748ef3a15cf6c43e62f9c0153852"}}