{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QM4ZZVUUD2OLNCXG4RHCIERRKW","short_pith_number":"pith:QM4ZZVUU","schema_version":"1.0","canonical_sha256":"83399cd6941e9cb68ae6e44e24123155ba8f373ce4944fd37b30f9813ec4fe72","source":{"kind":"arxiv","id":"2110.12612","version":2},"attestation_state":"computed","paper":{"title":"DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Gang Wang, Jinzhu Li, Kuan Chen, Lei He, Sheng Zhao, Xu Tan, Yanqing Liu, Zhihang Xu","submitted_at":"2021-10-25T02:47:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.12612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-25T02:47:59Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"5d004711e4fb9c22d0e97c3c3c094ca0f107a38e3088d484a03fd99ae049f92f","abstract_canon_sha256":"3a31f07f8319ad2f5faba16b560396792928bd5fe4b8e82d6b3588d8974f48f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:23.908153Z","signature_b64":"KnWhQJfwtNY6W+NV5jWKibA3vYD+iGUyX/1hWzN7ufEIUdHYF7girQOaAOyKCdM1hd8BTGCWy+XlPl4oKscmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83399cd6941e9cb68ae6e44e24123155ba8f373ce4944fd37b30f9813ec4fe72","last_reissued_at":"2026-07-05T03:33:23.907584Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:23.907584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Gang Wang, Jinzhu Li, Kuan Chen, Lei He, Sheng Zhao, Xu Tan, Yanqing Liu, Zhihang Xu","submitted_at":"2021-10-25T02:47:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12612","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.12612/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.12612","created_at":"2026-07-05T03:33:23.907660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.12612v2","created_at":"2026-07-05T03:33:23.907660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12612","created_at":"2026-07-05T03:33:23.907660+00:00"},{"alias_kind":"pith_short_12","alias_value":"QM4ZZVUUD2OL","created_at":"2026-07-05T03:33:23.907660+00:00"},{"alias_kind":"pith_short_16","alias_value":"QM4ZZVUUD2OLNCXG","created_at":"2026-07-05T03:33:23.907660+00:00"},{"alias_kind":"pith_short_8","alias_value":"QM4ZZVUU","created_at":"2026-07-05T03:33:23.907660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW","json":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW.json","graph_json":"https://pith.science/api/pith-number/QM4ZZVUUD2OLNCXG4RHCIERRKW/graph.json","events_json":"https://pith.science/api/pith-number/QM4ZZVUUD2OLNCXG4RHCIERRKW/events.json","paper":"https://pith.science/paper/QM4ZZVUU"},"agent_actions":{"view_html":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW","download_json":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW.json","view_paper":"https://pith.science/paper/QM4ZZVUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.12612&json=true","fetch_graph":"https://pith.science/api/pith-number/QM4ZZVUUD2OLNCXG4RHCIERRKW/graph.json","fetch_events":"https://pith.science/api/pith-number/QM4ZZVUUD2OLNCXG4RHCIERRKW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW/action/storage_attestation","attest_author":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW/action/author_attestation","sign_citation":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW/action/citation_signature","submit_replication":"https://pith.science/pith/QM4ZZVUUD2OLNCXG4RHCIERRKW/action/replication_record"}},"created_at":"2026-07-05T03:33:23.907660+00:00","updated_at":"2026-07-05T03:33:23.907660+00:00"}