{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QM4ZZVUUD2OLNCXG4RHCIERRKW","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":"3a31f07f8319ad2f5faba16b560396792928bd5fe4b8e82d6b3588d8974f48f6","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T02:47:59Z","title_canon_sha256":"5d004711e4fb9c22d0e97c3c3c094ca0f107a38e3088d484a03fd99ae049f92f"},"schema_version":"1.0","source":{"id":"2110.12612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12612","created_at":"2026-07-05T03:33:23Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12612v2","created_at":"2026-07-05T03:33:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12612","created_at":"2026-07-05T03:33:23Z"},{"alias_kind":"pith_short_12","alias_value":"QM4ZZVUUD2OL","created_at":"2026-07-05T03:33:23Z"},{"alias_kind":"pith_short_16","alias_value":"QM4ZZVUUD2OLNCXG","created_at":"2026-07-05T03:33:23Z"},{"alias_kind":"pith_short_8","alias_value":"QM4ZZVUU","created_at":"2026-07-05T03:33:23Z"}],"graph_snapshots":[{"event_id":"sha256:9ec6a533c6f6fef0e8b2a769732878a4491536d88d7868cc4569437a62506fc5","target":"graph","created_at":"2026-07-05T03:33:23Z","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/2110.12612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes the Microsoft end-to-end neural text to speech (TTS) system: DelightfulTTS for Blizzard Challenge 2021. The goal of this challenge is to synthesize natural and high-quality speech from text, and we approach this goal in two perspectives: The first is to directly model and generate waveform in 48 kHz sampling rate, which brings higher perception quality than previous systems with 16 kHz or 24 kHz sampling rate; The second is to model the variation information in speech through a systematic design, which improves the prosody and naturalness. Specifically, for 48 kHz modeling","authors_text":"Bohan Li, Gang Wang, Jinzhu Li, Kuan Chen, Lei He, Sheng Zhao, Xu Tan, Yanqing Liu, Zhihang Xu","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T02:47:59Z","title":"DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12612","kind":"arxiv","version":2},"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:ccf8a1d8ac594e3f3676b3721111f203dde3f596399a197871d0d440195ceca4","target":"record","created_at":"2026-07-05T03:33:23Z","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":"3a31f07f8319ad2f5faba16b560396792928bd5fe4b8e82d6b3588d8974f48f6","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T02:47:59Z","title_canon_sha256":"5d004711e4fb9c22d0e97c3c3c094ca0f107a38e3088d484a03fd99ae049f92f"},"schema_version":"1.0","source":{"id":"2110.12612","kind":"arxiv","version":2}},"canonical_sha256":"83399cd6941e9cb68ae6e44e24123155ba8f373ce4944fd37b30f9813ec4fe72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83399cd6941e9cb68ae6e44e24123155ba8f373ce4944fd37b30f9813ec4fe72","first_computed_at":"2026-07-05T03:33:23.907584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:23.907584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KnWhQJfwtNY6W+NV5jWKibA3vYD+iGUyX/1hWzN7ufEIUdHYF7girQOaAOyKCdM1hd8BTGCWy+XlPl4oKscmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:23.908153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccf8a1d8ac594e3f3676b3721111f203dde3f596399a197871d0d440195ceca4","sha256:9ec6a533c6f6fef0e8b2a769732878a4491536d88d7868cc4569437a62506fc5"],"state_sha256":"ff0727899c997981f287df6703c7677fb1182bcc24105b02d25fc14c5027a984"}