{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HXHQ5KHFJFIAOSRUXEWTHKKIZE","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":"7020c02adce0de1fbe4e79dfc936bf933a16a06904d284a2d532434407037787","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-15T05:28:23Z","title_canon_sha256":"5fc6f611eb8fe5d70292ebd9f9efc5b68559a3ce6e12b03be44b714f288fba11"},"schema_version":"1.0","source":{"id":"2202.07200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.07200","created_at":"2026-07-05T03:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.07200v2","created_at":"2026-07-05T03:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07200","created_at":"2026-07-05T03:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"HXHQ5KHFJFIA","created_at":"2026-07-05T03:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"HXHQ5KHFJFIAOSRU","created_at":"2026-07-05T03:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"HXHQ5KHF","created_at":"2026-07-05T03:57:32Z"}],"graph_snapshots":[{"event_id":"sha256:f93ab1850ec664bb11f8b096abbdcea9cc3f90c736db8b981a52d999260f2152","target":"graph","created_at":"2026-07-05T03:57:32Z","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/2202.07200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although word-level prosody modeling in neural text-to-speech (TTS) has been investigated in recent research for diverse speech synthesis, it is still challenging to control speech synthesis manually without a specific reference. This is largely due to lack of word-level prosody tags. In this work, we propose a novel approach for unsupervised word-level prosody tagging with two stages, where we first group the words into different types with a decision tree according to their phonetic content and then cluster the prosodies using GMM within each type of words separately. This design is based on","authors_text":"Chenpeng Du, Kai Yu, Yiwei Guo","cross_cats":["cs.AI","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-15T05:28:23Z","title":"Unsupervised word-level prosody tagging for controllable speech synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07200","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":"sha256:61815b676f14701f670aedcda9f68d69e817047417a0c31903612e8d2cf1f1ca","target":"record","created_at":"2026-07-05T03:57:32Z","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":"7020c02adce0de1fbe4e79dfc936bf933a16a06904d284a2d532434407037787","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-15T05:28:23Z","title_canon_sha256":"5fc6f611eb8fe5d70292ebd9f9efc5b68559a3ce6e12b03be44b714f288fba11"},"schema_version":"1.0","source":{"id":"2202.07200","kind":"arxiv","version":2}},"canonical_sha256":"3dcf0ea8e54950074a34b92d33a948c93e44336cdc9718e648c06cdd2f2e84d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dcf0ea8e54950074a34b92d33a948c93e44336cdc9718e648c06cdd2f2e84d8","first_computed_at":"2026-07-05T03:57:32.390051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:32.390051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fRixwZ6mxfQ/6akHUcKbwCJlMK0fI6noBg4R3ES3+JF1/65DFm6f0pdjPvWapQUAB0LJ2D2q1XFQgTRyx9+jAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:32.390522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.07200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61815b676f14701f670aedcda9f68d69e817047417a0c31903612e8d2cf1f1ca","sha256:f93ab1850ec664bb11f8b096abbdcea9cc3f90c736db8b981a52d999260f2152"],"state_sha256":"195843019f5f91afb0b5155f89dc896215b3cfe7b90cd7601a0bbbc8327c0c8a"}