{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QUP4IQW457TGQMPO7N2Y4RYZJQ","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":"cc56f0836db043c52adb7e6afb2b0d6f7dcd86e576cfdefce2be6f3ffc4e2bbb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-11T23:14:07Z","title_canon_sha256":"089989e269a493031342637db6a0ef3c6dda604621f99a3904df197d6dda0205"},"schema_version":"1.0","source":{"id":"2507.09070","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09070","created_at":"2026-07-05T11:36:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09070v1","created_at":"2026-07-05T11:36:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09070","created_at":"2026-07-05T11:36:03Z"},{"alias_kind":"pith_short_12","alias_value":"QUP4IQW457TG","created_at":"2026-07-05T11:36:03Z"},{"alias_kind":"pith_short_16","alias_value":"QUP4IQW457TGQMPO","created_at":"2026-07-05T11:36:03Z"},{"alias_kind":"pith_short_8","alias_value":"QUP4IQW4","created_at":"2026-07-05T11:36:03Z"}],"graph_snapshots":[{"event_id":"sha256:0b1dfc07753b55a62bbb4319c0af326368d2d03688d46de16c046e7e993027ce","target":"graph","created_at":"2026-07-05T11:36:03Z","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/2507.09070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot voice conversion (VC) synthesizes speech in a target speaker's voice while preserving linguistic and paralinguistic content. However, timbre leakage-where source speaker traits persist-remains a challenge, especially in neural codec and LLM-based VC, where quantized representations entangle speaker identity with content. We introduce SemAlignVC, an architecture designed to prevent timbre leakage using SemAlign, a novel method that aligns text and audio representations to ensure speaker-independent semantic encoding. This disentangled representation conditions an autoregressive transf","authors_text":"Kainan Peng, Mike Seltzer, Mingbo Ma, Qing He, Shivam Mehta, Shun Zhang, Vimal Manohar, Yingru Liu, Zhenyu Tang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-11T23:14:07Z","title":"SemAlignVC: Enhancing zero-shot timbre conversion using semantic alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09070","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:e9d5c16a9f2887af1c4486b041ee9c0ff8b45d44bb37c4716b54baf32c8046d8","target":"record","created_at":"2026-07-05T11:36:03Z","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":"cc56f0836db043c52adb7e6afb2b0d6f7dcd86e576cfdefce2be6f3ffc4e2bbb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-07-11T23:14:07Z","title_canon_sha256":"089989e269a493031342637db6a0ef3c6dda604621f99a3904df197d6dda0205"},"schema_version":"1.0","source":{"id":"2507.09070","kind":"arxiv","version":1}},"canonical_sha256":"851fc442dcefe66831eefb758e47194c3a8397a88086634d014b4306d3fe095e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"851fc442dcefe66831eefb758e47194c3a8397a88086634d014b4306d3fe095e","first_computed_at":"2026-07-05T11:36:03.148969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:03.148969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w/PaJeNw2tGPuW4czbMhvT3IOIFlYOuRMAuRDpJkVkKN2fdUzh5//43KGa5yf5eP2tky4Lc5/W9sAQGpybbQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:03.149442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09070","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9d5c16a9f2887af1c4486b041ee9c0ff8b45d44bb37c4716b54baf32c8046d8","sha256:0b1dfc07753b55a62bbb4319c0af326368d2d03688d46de16c046e7e993027ce"],"state_sha256":"9dc5dbad3addf06a6c1abeb4e070cadeaba83f23a3ff1544d01fa2e557aed5ee"}