{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QVW4UP4HW2WEZLA3XZR6V6QIV2","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":"c9275c39f344c5b00ac973bcdaa30187669fe706353085605c4d1cf5d2a4a564","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T01:34:29Z","title_canon_sha256":"13f5c5d88d40309db82a63861268886659f93fc57d922908be3af6836cb2a109"},"schema_version":"1.0","source":{"id":"2505.13805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13805","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13805v1","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13805","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"QVW4UP4HW2WE","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"QVW4UP4HW2WEZLA3","created_at":"2026-07-05T11:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"QVW4UP4H","created_at":"2026-07-05T11:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:75816434722fe29a2ff310174bb081f5ae6da0ac39dbb23391130218ee65d06b","target":"graph","created_at":"2026-07-05T11:05:51Z","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/2505.13805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite great advances, achieving high-fidelity emotional voice conversion (EVC) with flexible and interpretable control remains challenging. This paper introduces ClapFM-EVC, a novel EVC framework capable of generating high-quality converted speech driven by natural language prompts or reference speech with adjustable emotion intensity. We first propose EVC-CLAP, an emotional contrastive language-audio pre-training model, guided by natural language prompts and categorical labels, to extract and align fine-grained emotional elements across speech and text modalities. Then, a FuEncoder with an ","authors_text":"Hongbin Zhou, Jianhao Ye, Jianjun Zhao, Jixun Yao, Lei Ma, Yanni Hu, Yuguang Yang, Yu Pan","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T01:34:29Z","title":"ClapFM-EVC: High-Fidelity and Flexible Emotional Voice Conversion with Dual Control from Natural Language and Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13805","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":"sha256:9820d64d400879ae238e7a0881c7b4b3b8054ea04c5527dfcc0925963b84e7ad","target":"record","created_at":"2026-07-05T11:05:51Z","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":"c9275c39f344c5b00ac973bcdaa30187669fe706353085605c4d1cf5d2a4a564","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-20T01:34:29Z","title_canon_sha256":"13f5c5d88d40309db82a63861268886659f93fc57d922908be3af6836cb2a109"},"schema_version":"1.0","source":{"id":"2505.13805","kind":"arxiv","version":1}},"canonical_sha256":"856dca3f87b6ac4cac1bbe63eafa08ae856f6632f4ae9a66f6fec49aa4c04493","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"856dca3f87b6ac4cac1bbe63eafa08ae856f6632f4ae9a66f6fec49aa4c04493","first_computed_at":"2026-07-05T11:05:51.285927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:51.285927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jtKgA7Ju6tZK5FInIsYk+wCCxQLvi8JGMgwIVmETt9t4f24yfy/g9gQ2M1OQ+xY0phtM4OhyGS25CwyYNb/9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:51.286386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9820d64d400879ae238e7a0881c7b4b3b8054ea04c5527dfcc0925963b84e7ad","sha256:75816434722fe29a2ff310174bb081f5ae6da0ac39dbb23391130218ee65d06b"],"state_sha256":"e1aef7bf277483aa6af0638519bc0a1c60a75e34633181212a7f8de83825c6ae"}