{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4SHB2JUMZNP5VCBEDRFPKGLMAC","short_pith_number":"pith:4SHB2JUM","schema_version":"1.0","canonical_sha256":"e48e1d268ccb5fda88241c4af5196c00877109e2bfb254097bfe69beb1f6a07e","source":{"kind":"arxiv","id":"2409.06451","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Kun Zhou, Xin Jing","submitted_at":"2024-09-10T12:13:24Z","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"},"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":"2409.06451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-10T12:13:24Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e01007656c71c06de0ad5a16cb7795e10c016e6bb29dc00786a4042d05b371f2","abstract_canon_sha256":"a74ba8a96df75ff442361e9122c19462c86494f7b230a5cb660e51c99fdd3606"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:24.710496Z","signature_b64":"AcwlNNYDI9YHTyHA0khG/7FllkGvhxna9MCUW8mDn6kq4P0KYr8LVgz9CXp4E3mSH4RzN1bMhpUmJnrD8TyPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e48e1d268ccb5fda88241c4af5196c00877109e2bfb254097bfe69beb1f6a07e","last_reissued_at":"2026-07-05T09:05:24.709962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:24.709962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Kun Zhou, Xin Jing","submitted_at":"2024-09-10T12:13:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06451","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/2409.06451/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":"2409.06451","created_at":"2026-07-05T09:05:24.710035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06451v1","created_at":"2026-07-05T09:05:24.710035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06451","created_at":"2026-07-05T09:05:24.710035+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SHB2JUMZNP5","created_at":"2026-07-05T09:05:24.710035+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SHB2JUMZNP5VCBE","created_at":"2026-07-05T09:05:24.710035+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SHB2JUM","created_at":"2026-07-05T09:05:24.710035+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/4SHB2JUMZNP5VCBEDRFPKGLMAC","json":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC.json","graph_json":"https://pith.science/api/pith-number/4SHB2JUMZNP5VCBEDRFPKGLMAC/graph.json","events_json":"https://pith.science/api/pith-number/4SHB2JUMZNP5VCBEDRFPKGLMAC/events.json","paper":"https://pith.science/paper/4SHB2JUM"},"agent_actions":{"view_html":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC","download_json":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC.json","view_paper":"https://pith.science/paper/4SHB2JUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06451&json=true","fetch_graph":"https://pith.science/api/pith-number/4SHB2JUMZNP5VCBEDRFPKGLMAC/graph.json","fetch_events":"https://pith.science/api/pith-number/4SHB2JUMZNP5VCBEDRFPKGLMAC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC/action/storage_attestation","attest_author":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC/action/author_attestation","sign_citation":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC/action/citation_signature","submit_replication":"https://pith.science/pith/4SHB2JUMZNP5VCBEDRFPKGLMAC/action/replication_record"}},"created_at":"2026-07-05T09:05:24.710035+00:00","updated_at":"2026-07-05T09:05:24.710035+00:00"}