{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6DYIHCTJQKROEIPSGBHLZVPGHE","short_pith_number":"pith:6DYIHCTJ","schema_version":"1.0","canonical_sha256":"f0f0838a6982a2e221f2304ebcd5e63912a8bc101b12eb1894f9a65238bd923e","source":{"kind":"arxiv","id":"2104.04050","version":1},"attestation_state":"computed","paper":{"title":"Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Gaurav Bharaj, Mahsa Elyasi","submitted_at":"2021-04-08T20:50:15Z","abstract_excerpt":"Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural speech, Tacotron-2's encoder doesn't fully represent prosodic features (e.g. syllable stress in English) from characters, and result in flat fundamental frequency variations.\n  In this work, we propose a novel carefully designed strategy for conditioning Tacotron-2 on two fundamental prosodic features in English -- stress syllable and pitch accent, that help ac"},"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":"2104.04050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-08T20:50:15Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"439009ba1acdf2c3b5f671bc89950e591311705f16c162f4afff166cbeabacad","abstract_canon_sha256":"85d76a5dd4872ebf1400aabdec07ae851b8dd06195391df2d21786b845167030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:34.236373Z","signature_b64":"XNCTRnS4sDuQEUz6lK6yGZUtj8nRjTHlifjiHCTi4djaTbPqQ13ig/6DScno+kgy2Z0j4ViGH02/Tf67NwjXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0f0838a6982a2e221f2304ebcd5e63912a8bc101b12eb1894f9a65238bd923e","last_reissued_at":"2026-07-05T02:30:34.235811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:34.235811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flavored Tacotron: Conditional Learning for Prosodic-linguistic Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Gaurav Bharaj, Mahsa Elyasi","submitted_at":"2021-04-08T20:50:15Z","abstract_excerpt":"Neural sequence-to-sequence text-to-speech synthesis (TTS), such as Tacotron-2, transforms text into high-quality speech. However, generating speech with natural prosody still remains a challenge. Yasuda et. al. show that unlike natural speech, Tacotron-2's encoder doesn't fully represent prosodic features (e.g. syllable stress in English) from characters, and result in flat fundamental frequency variations.\n  In this work, we propose a novel carefully designed strategy for conditioning Tacotron-2 on two fundamental prosodic features in English -- stress syllable and pitch accent, that help ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04050","kind":"arxiv","version":1},"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/2104.04050/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":"2104.04050","created_at":"2026-07-05T02:30:34.235873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04050v1","created_at":"2026-07-05T02:30:34.235873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04050","created_at":"2026-07-05T02:30:34.235873+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DYIHCTJQKRO","created_at":"2026-07-05T02:30:34.235873+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DYIHCTJQKROEIPS","created_at":"2026-07-05T02:30:34.235873+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DYIHCTJ","created_at":"2026-07-05T02:30:34.235873+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/6DYIHCTJQKROEIPSGBHLZVPGHE","json":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE.json","graph_json":"https://pith.science/api/pith-number/6DYIHCTJQKROEIPSGBHLZVPGHE/graph.json","events_json":"https://pith.science/api/pith-number/6DYIHCTJQKROEIPSGBHLZVPGHE/events.json","paper":"https://pith.science/paper/6DYIHCTJ"},"agent_actions":{"view_html":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE","download_json":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE.json","view_paper":"https://pith.science/paper/6DYIHCTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04050&json=true","fetch_graph":"https://pith.science/api/pith-number/6DYIHCTJQKROEIPSGBHLZVPGHE/graph.json","fetch_events":"https://pith.science/api/pith-number/6DYIHCTJQKROEIPSGBHLZVPGHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE/action/storage_attestation","attest_author":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE/action/author_attestation","sign_citation":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE/action/citation_signature","submit_replication":"https://pith.science/pith/6DYIHCTJQKROEIPSGBHLZVPGHE/action/replication_record"}},"created_at":"2026-07-05T02:30:34.235873+00:00","updated_at":"2026-07-05T02:30:34.235873+00:00"}