{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TKWGI2KIOTHBQXHXV32HGL5UAB","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":"8efbf80ca4dbb4cc993484fe585df94304a3244c1ed3cac9759901626f146482","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T08:00:56Z","title_canon_sha256":"bc866fe99934111cdfd1d3a0f3f5972c2490e8952f58cff39c7840c2eb84bbff"},"schema_version":"1.0","source":{"id":"2506.07036","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07036","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07036v2","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07036","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"TKWGI2KIOTHB","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"TKWGI2KIOTHBQXHX","created_at":"2026-07-05T11:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"TKWGI2KI","created_at":"2026-07-05T11:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:cfb2037bd7db0fff36b22ca981af2285d57cc6535fc3397cee40397783825b75","target":"graph","created_at":"2026-07-05T11:20:55Z","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/2506.07036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose TES-VC (Text-driven Environment and Speaker controllable Voice Conversion), a text-driven voice conversion framework with independent control of speaker timbre and environmental acoustics. TES-VC processes simultaneous text inputs for target voice and environment, accurately generating speech matching described timbre/environment while preserving source content. Trained on synthetic data with decoupled vocal/environment features via latent diffusion modeling, our method eliminates interference between attributes. The Retrieval-Based Timbre Control (RBTC) module enables precise manip","authors_text":"Jiawei Jin, Yixuan Zhou, Zhihan Yang, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T08:00:56Z","title":"In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07036","kind":"arxiv","version":2},"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:d0371607cb937fcc125764433bd6c10f7b63746f398acb3a0ab70bb3278cd3b4","target":"record","created_at":"2026-07-05T11:20:55Z","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":"8efbf80ca4dbb4cc993484fe585df94304a3244c1ed3cac9759901626f146482","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-08T08:00:56Z","title_canon_sha256":"bc866fe99934111cdfd1d3a0f3f5972c2490e8952f58cff39c7840c2eb84bbff"},"schema_version":"1.0","source":{"id":"2506.07036","kind":"arxiv","version":2}},"canonical_sha256":"9aac64694874ce185cf7aef4732fb4004bc244bc1db764c6cfa97913483f9cab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9aac64694874ce185cf7aef4732fb4004bc244bc1db764c6cfa97913483f9cab","first_computed_at":"2026-07-05T11:20:55.533285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:20:55.533285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nx+NA+G5QITjilM9fjHiP0Vkaq46ruuttxO2K1mF1jt7JEL4WjGuashdtyHkzC3akYNfsNEc0AbpLp/CIWu8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:20:55.533780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07036","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0371607cb937fcc125764433bd6c10f7b63746f398acb3a0ab70bb3278cd3b4","sha256:cfb2037bd7db0fff36b22ca981af2285d57cc6535fc3397cee40397783825b75"],"state_sha256":"4ba7bb788910a7a46822ffd771c2e039ea96868b92cacf86de3282a3293fd6c6"}