{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7N64U3D4ZPTEYIU66JJ2KTQ3I3","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":"6870305a4a3cf246b1b43c7f1075465e39391eebdebca25d18c6fa4a81b011ae","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-28T06:37:52Z","title_canon_sha256":"d6d9065ba4fb1ab5a33f1638a1e25c3e9783d123179bd8e02a9b55f44b0cf82b"},"schema_version":"1.0","source":{"id":"2312.16850","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16850","created_at":"2026-07-05T07:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16850v2","created_at":"2026-07-05T07:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16850","created_at":"2026-07-05T07:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"7N64U3D4ZPTE","created_at":"2026-07-05T07:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"7N64U3D4ZPTEYIU6","created_at":"2026-07-05T07:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"7N64U3D4","created_at":"2026-07-05T07:28:48Z"}],"graph_snapshots":[{"event_id":"sha256:9e0ad008c4b2abf9799e685166d105edd14163853ca09f2e3ad1c52bbd18c420","target":"graph","created_at":"2026-07-05T07:28:48Z","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/2312.16850/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accent transfer aims to transfer an accent from a source speaker to synthetic speech in the target speaker's voice. The main challenge is how to effectively disentangle speaker timbre and accent which are entangled in speech. This paper presents a VITS-based end-to-end accent transfer model named Accent-VITS.Based on the main structure of VITS, Accent-VITS makes substantial improvements to enable effective and stable accent transfer.We leverage a hierarchical CVAE structure to model accent pronunciation information and acoustic features, respectively, using bottleneck features and mel spectrum","authors_text":"Lei Xie, Linhan Ma, Pengcheng Zhu, Xinfa Zhu, Yi Lei, Yongmao Zhang, Ziqian Ning","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-28T06:37:52Z","title":"Accent-VITS:accent transfer for end-to-end TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16850","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:e298a7f02fbd5c654e518e1974447d6b251f4e3efb9ff08c512490b1c2d82ffd","target":"record","created_at":"2026-07-05T07:28:48Z","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":"6870305a4a3cf246b1b43c7f1075465e39391eebdebca25d18c6fa4a81b011ae","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-28T06:37:52Z","title_canon_sha256":"d6d9065ba4fb1ab5a33f1638a1e25c3e9783d123179bd8e02a9b55f44b0cf82b"},"schema_version":"1.0","source":{"id":"2312.16850","kind":"arxiv","version":2}},"canonical_sha256":"fb7dca6c7ccbe64c229ef253a54e1b46d285e5cff6a2236b73a214639fc5ee6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb7dca6c7ccbe64c229ef253a54e1b46d285e5cff6a2236b73a214639fc5ee6b","first_computed_at":"2026-07-05T07:28:48.303846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:48.303846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YQ+4IaRRp1+Ek4uh04pVRWD7EyPJ6jbnN69F39940gzJJ2fXNAtRlcvqSBa1um8IAcU7bFQlaYqLjKHaflr7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:48.304347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16850","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e298a7f02fbd5c654e518e1974447d6b251f4e3efb9ff08c512490b1c2d82ffd","sha256:9e0ad008c4b2abf9799e685166d105edd14163853ca09f2e3ad1c52bbd18c420"],"state_sha256":"c5ed6399d18d87a3b7f022ab41df21dc866e1a710241ebfbb84eb8f343e3b928"}