{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4V6DBGFCHD3QQZMSE2KXJN5ID3","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":"775ab618869a56f732a7a14e608d777d25b768a9042ea00a9dde0054cc08ad0d","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-12T17:57:17Z","title_canon_sha256":"215b26c17e022b2c648b79faeaca9291f0ad29ac6d555c0a285a342ab333cea0"},"schema_version":"1.0","source":{"id":"2005.05957","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05957","created_at":"2026-07-05T01:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05957v3","created_at":"2026-07-05T01:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05957","created_at":"2026-07-05T01:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"4V6DBGFCHD3Q","created_at":"2026-07-05T01:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"4V6DBGFCHD3QQZMS","created_at":"2026-07-05T01:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"4V6DBGFC","created_at":"2026-07-05T01:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:b3cc2623eccc4c3de142cef57a94e707ab36bd105ddf0c205254529645e24a71","target":"graph","created_at":"2026-07-05T01:19:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.05957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we propose Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis with control over speech variation and style transfer. Flowtron borrows insights from IAF and revamps Tacotron in order to provide high-quality and expressive mel-spectrogram synthesis. Flowtron is optimized by maximizing the likelihood of the training data, which makes training simple and stable. Flowtron learns an invertible mapping of data to a latent space that can be manipulated to control many aspects of speech synthesis (pitch, tone, speech rate, cadence, accent). Our mean opi","authors_text":"Bryan Catanzaro, Kevin Shih, Rafael Valle, Ryan Prenger","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-12T17:57:17Z","title":"Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05957","kind":"arxiv","version":3},"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":"sha256:808fe9489fec542c046ce1cdcce4eb85ddcbaf36bf90cc8475bc94c0c4cb7308","target":"record","created_at":"2026-07-05T01:19:39Z","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":"775ab618869a56f732a7a14e608d777d25b768a9042ea00a9dde0054cc08ad0d","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-05-12T17:57:17Z","title_canon_sha256":"215b26c17e022b2c648b79faeaca9291f0ad29ac6d555c0a285a342ab333cea0"},"schema_version":"1.0","source":{"id":"2005.05957","kind":"arxiv","version":3}},"canonical_sha256":"e57c3098a238f7086592269574b7a81ee9a6128eb4171ec72765e7e639d44c1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e57c3098a238f7086592269574b7a81ee9a6128eb4171ec72765e7e639d44c1c","first_computed_at":"2026-07-05T01:19:39.782844Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:19:39.782844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W8ALzl/D9BI9S7qOSjIJReMxKsvqb1PoagFDRVv/k+1Ikcu61ZUjE8Rel6xdqqs2KK/1I/j9NevnuVhXA/bxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:19:39.783334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.05957","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:808fe9489fec542c046ce1cdcce4eb85ddcbaf36bf90cc8475bc94c0c4cb7308","sha256:b3cc2623eccc4c3de142cef57a94e707ab36bd105ddf0c205254529645e24a71"],"state_sha256":"4b9a9a688e7380024fee3da1c2c6064e91c3212fade84506be31c4a156b568d0"}