{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YB7375IMJEWPJFAF2DFH7U3F6Q","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":"81e4d7931aa1d759f7b548cda288d52c8ea33efa8456d76911eeb5cffa268457","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T17:50:21Z","title_canon_sha256":"62489d8a888a10d2c8e572b40c23b71c3024d57a9a3da5f4207e668c27023e5a"},"schema_version":"1.0","source":{"id":"1905.09263","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09263","created_at":"2026-07-05T00:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09263v5","created_at":"2026-07-05T00:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09263","created_at":"2026-07-05T00:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"YB7375IMJEWP","created_at":"2026-07-05T00:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"YB7375IMJEWPJFAF","created_at":"2026-07-05T00:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"YB7375IM","created_at":"2026-07-05T00:20:43Z"}],"graph_snapshots":[{"event_id":"sha256:0f193621de3fadc3a6d0dcc4786d2c340dd58730022689328975122086594854","target":"graph","created_at":"2026-07-05T00:20:43Z","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/1905.09263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural network based end-to-end text to speech (TTS) has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron 2) usually first generate mel-spectrogram from text, and then synthesize speech from the mel-spectrogram using vocoder such as WaveNet. Compared with traditional concatenative and statistical parametric approaches, neural network based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust (i.e., some words are skipped or repeated) and lack of controllability (voice speed or prosody control). In this w","authors_text":"Sheng Zhao, Tao Qin, Tie-Yan Liu, Xu Tan, Yangjun Ruan, Yi Ren, Zhou Zhao","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T17:50:21Z","title":"FastSpeech: Fast, Robust and Controllable Text to Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09263","kind":"arxiv","version":5},"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:ab015b9740f1aeaed3940f6a79d62570d4e5907fc89f32b05e0d390565c20c22","target":"record","created_at":"2026-07-05T00:20:43Z","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":"81e4d7931aa1d759f7b548cda288d52c8ea33efa8456d76911eeb5cffa268457","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-22T17:50:21Z","title_canon_sha256":"62489d8a888a10d2c8e572b40c23b71c3024d57a9a3da5f4207e668c27023e5a"},"schema_version":"1.0","source":{"id":"1905.09263","kind":"arxiv","version":5}},"canonical_sha256":"c07fbff50c492cf49405d0ca7fd365f409a25215325216962948363638c523ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c07fbff50c492cf49405d0ca7fd365f409a25215325216962948363638c523ab","first_computed_at":"2026-07-05T00:20:43.277924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:43.277924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yZjPGnmJLN1Ubqfs8ANcCDIfTLrK0cZ8ghM+2DzPXs6YzVtY2T+WviFgFvL3MOox760vOXdSzbfkZSY7EjKDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:43.278397Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09263","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab015b9740f1aeaed3940f6a79d62570d4e5907fc89f32b05e0d390565c20c22","sha256:0f193621de3fadc3a6d0dcc4786d2c340dd58730022689328975122086594854"],"state_sha256":"aa140859e83385f20917a66ad8cbe00200187f0b4db51bb45b0d8a10c42446b0"}