{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4SHB2JUMZNP5VCBEDRFPKGLMAC","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":"a74ba8a96df75ff442361e9122c19462c86494f7b230a5cb660e51c99fdd3606","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T12:13:24Z","title_canon_sha256":"e01007656c71c06de0ad5a16cb7795e10c016e6bb29dc00786a4042d05b371f2"},"schema_version":"1.0","source":{"id":"2409.06451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.06451","created_at":"2026-07-05T09:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2409.06451v1","created_at":"2026-07-05T09:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06451","created_at":"2026-07-05T09:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"4SHB2JUMZNP5","created_at":"2026-07-05T09:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"4SHB2JUMZNP5VCBE","created_at":"2026-07-05T09:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"4SHB2JUM","created_at":"2026-07-05T09:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:f637b7f0414c1d0a4d573c998d0457804f39c31679a5b74cbb09bd3fd116e6fa","target":"graph","created_at":"2026-07-05T09:05:24Z","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/2409.06451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While current emotional text-to-speech (TTS) systems can generate highly intelligible emotional speech, achieving fine control over emotion rendering of the output speech still remains a significant challenge. In this paper, we introduce ParaEVITS, a novel emotional TTS framework that leverages the compositionality of natural language to enhance control over emotional rendering. By incorporating a text-audio encoder inspired by ParaCLAP, a contrastive language-audio pretraining (CLAP) model for computational paralinguistics, the diffusion model is trained to generate emotional embeddings based","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Kun Zhou, Xin Jing","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T12:13:24Z","title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06451","kind":"arxiv","version":1},"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:bc31cb47d9c17956609c11148edcff0c4ffcb5d475029bfb59fc348d16639f97","target":"record","created_at":"2026-07-05T09:05:24Z","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":"a74ba8a96df75ff442361e9122c19462c86494f7b230a5cb660e51c99fdd3606","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T12:13:24Z","title_canon_sha256":"e01007656c71c06de0ad5a16cb7795e10c016e6bb29dc00786a4042d05b371f2"},"schema_version":"1.0","source":{"id":"2409.06451","kind":"arxiv","version":1}},"canonical_sha256":"e48e1d268ccb5fda88241c4af5196c00877109e2bfb254097bfe69beb1f6a07e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e48e1d268ccb5fda88241c4af5196c00877109e2bfb254097bfe69beb1f6a07e","first_computed_at":"2026-07-05T09:05:24.709962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:24.709962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AcwlNNYDI9YHTyHA0khG/7FllkGvhxna9MCUW8mDn6kq4P0KYr8LVgz9CXp4E3mSH4RzN1bMhpUmJnrD8TyPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:24.710496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.06451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc31cb47d9c17956609c11148edcff0c4ffcb5d475029bfb59fc348d16639f97","sha256:f637b7f0414c1d0a4d573c998d0457804f39c31679a5b74cbb09bd3fd116e6fa"],"state_sha256":"39238b7a50b265a14e29321c74277a9b9e158f99a7ea3b656f9fdb44f512f4cf"}