{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UBITUMJOPDFUS42DC3H6ELP6OS","short_pith_number":"pith:UBITUMJO","schema_version":"1.0","canonical_sha256":"a0513a312e78cb49734316cfe22dfe74b72c567fe3524feee6de37b91310a1da","source":{"kind":"arxiv","id":"2507.12015","version":1},"attestation_state":"computed","paper":{"title":"EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoxun Li, Jiaxi Hu, Leyuan Qu, Taihao Li","submitted_at":"2025-07-16T08:19:20Z","abstract_excerpt":"In recent years, emotional Text-to-Speech (TTS) synthesis and emphasis-controllable speech synthesis have advanced significantly. However, their interaction remains underexplored. We propose Emphasis Meets Emotion TTS (EME-TTS), a novel framework designed to address two key research questions: (1) how to effectively utilize emphasis to enhance the expressiveness of emotional speech, and (2) how to maintain the perceptual clarity and stability of target emphasis across different emotions. EME-TTS employs weakly supervised learning with emphasis pseudo-labels and variance-based emphasis features"},"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":"2507.12015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-16T08:19:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f3803c701b9cce3e4642e5c1ae6cf391e7f2b70b32ec0503e32cf08145baf6e7","abstract_canon_sha256":"78f0c57c39fc70b8a2ad7c3094aec65b1f160a3461f405ab80ddb72abfd0bac6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:12.946254Z","signature_b64":"HKOEpKIQ6w8ZmIYQX4AQF7QZaiw2koWRwE4qG8dO1JvfmlJohemPxBVic1etZcZdFfo2ZbO2LFy9vAWOrdSkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0513a312e78cb49734316cfe22dfe74b72c567fe3524feee6de37b91310a1da","last_reissued_at":"2026-07-05T11:38:12.945707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:12.945707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haoxun Li, Jiaxi Hu, Leyuan Qu, Taihao Li","submitted_at":"2025-07-16T08:19:20Z","abstract_excerpt":"In recent years, emotional Text-to-Speech (TTS) synthesis and emphasis-controllable speech synthesis have advanced significantly. However, their interaction remains underexplored. We propose Emphasis Meets Emotion TTS (EME-TTS), a novel framework designed to address two key research questions: (1) how to effectively utilize emphasis to enhance the expressiveness of emotional speech, and (2) how to maintain the perceptual clarity and stability of target emphasis across different emotions. EME-TTS employs weakly supervised learning with emphasis pseudo-labels and variance-based emphasis features"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12015","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/2507.12015/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":"2507.12015","created_at":"2026-07-05T11:38:12.945769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12015v1","created_at":"2026-07-05T11:38:12.945769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12015","created_at":"2026-07-05T11:38:12.945769+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBITUMJOPDFU","created_at":"2026-07-05T11:38:12.945769+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBITUMJOPDFUS42D","created_at":"2026-07-05T11:38:12.945769+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBITUMJO","created_at":"2026-07-05T11:38:12.945769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12015","citing_title":"EME-TTS: Unlocking the Emphasis and Emotion Link in Speech Synthesis","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS","json":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS.json","graph_json":"https://pith.science/api/pith-number/UBITUMJOPDFUS42DC3H6ELP6OS/graph.json","events_json":"https://pith.science/api/pith-number/UBITUMJOPDFUS42DC3H6ELP6OS/events.json","paper":"https://pith.science/paper/UBITUMJO"},"agent_actions":{"view_html":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS","download_json":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS.json","view_paper":"https://pith.science/paper/UBITUMJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12015&json=true","fetch_graph":"https://pith.science/api/pith-number/UBITUMJOPDFUS42DC3H6ELP6OS/graph.json","fetch_events":"https://pith.science/api/pith-number/UBITUMJOPDFUS42DC3H6ELP6OS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS/action/storage_attestation","attest_author":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS/action/author_attestation","sign_citation":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS/action/citation_signature","submit_replication":"https://pith.science/pith/UBITUMJOPDFUS42DC3H6ELP6OS/action/replication_record"}},"created_at":"2026-07-05T11:38:12.945769+00:00","updated_at":"2026-07-05T11:38:12.945769+00:00"}