{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HXHQ5KHFJFIAOSRUXEWTHKKIZE","short_pith_number":"pith:HXHQ5KHF","schema_version":"1.0","canonical_sha256":"3dcf0ea8e54950074a34b92d33a948c93e44336cdc9718e648c06cdd2f2e84d8","source":{"kind":"arxiv","id":"2202.07200","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised word-level prosody tagging for controllable speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Kai Yu, Yiwei Guo","submitted_at":"2022-02-15T05:28:23Z","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"},"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":"2202.07200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-02-15T05:28:23Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD"],"title_canon_sha256":"5fc6f611eb8fe5d70292ebd9f9efc5b68559a3ce6e12b03be44b714f288fba11","abstract_canon_sha256":"7020c02adce0de1fbe4e79dfc936bf933a16a06904d284a2d532434407037787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:32.390522Z","signature_b64":"fRixwZ6mxfQ/6akHUcKbwCJlMK0fI6noBg4R3ES3+JF1/65DFm6f0pdjPvWapQUAB0LJ2D2q1XFQgTRyx9+jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dcf0ea8e54950074a34b92d33a948c93e44336cdc9718e648c06cdd2f2e84d8","last_reissued_at":"2026-07-05T03:57:32.390051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:32.390051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised word-level prosody tagging for controllable speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenpeng Du, Kai Yu, Yiwei Guo","submitted_at":"2022-02-15T05:28:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.07200","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/2202.07200/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":"2202.07200","created_at":"2026-07-05T03:57:32.390111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.07200v2","created_at":"2026-07-05T03:57:32.390111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.07200","created_at":"2026-07-05T03:57:32.390111+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXHQ5KHFJFIA","created_at":"2026-07-05T03:57:32.390111+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXHQ5KHFJFIAOSRU","created_at":"2026-07-05T03:57:32.390111+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXHQ5KHF","created_at":"2026-07-05T03:57:32.390111+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/HXHQ5KHFJFIAOSRUXEWTHKKIZE","json":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE.json","graph_json":"https://pith.science/api/pith-number/HXHQ5KHFJFIAOSRUXEWTHKKIZE/graph.json","events_json":"https://pith.science/api/pith-number/HXHQ5KHFJFIAOSRUXEWTHKKIZE/events.json","paper":"https://pith.science/paper/HXHQ5KHF"},"agent_actions":{"view_html":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE","download_json":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE.json","view_paper":"https://pith.science/paper/HXHQ5KHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.07200&json=true","fetch_graph":"https://pith.science/api/pith-number/HXHQ5KHFJFIAOSRUXEWTHKKIZE/graph.json","fetch_events":"https://pith.science/api/pith-number/HXHQ5KHFJFIAOSRUXEWTHKKIZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE/action/storage_attestation","attest_author":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE/action/author_attestation","sign_citation":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE/action/citation_signature","submit_replication":"https://pith.science/pith/HXHQ5KHFJFIAOSRUXEWTHKKIZE/action/replication_record"}},"created_at":"2026-07-05T03:57:32.390111+00:00","updated_at":"2026-07-05T03:57:32.390111+00:00"}