{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:G5X6NNMNOKF3PSCTZQMVAKHWAI","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":"08a91886d240999ae9ecf70e6522b61195ddc3f78b5182c781f41feedb9a1946","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-31T04:56:14Z","title_canon_sha256":"200d51bbbb54484deaf528a2b9a56aaa1f7281aa77eaf183606ab6e94ccaef0d"},"schema_version":"1.0","source":{"id":"2103.16809","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16809","created_at":"2026-07-05T02:47:43Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16809v2","created_at":"2026-07-05T02:47:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16809","created_at":"2026-07-05T02:47:43Z"},{"alias_kind":"pith_short_12","alias_value":"G5X6NNMNOKF3","created_at":"2026-07-05T02:47:43Z"},{"alias_kind":"pith_short_16","alias_value":"G5X6NNMNOKF3PSCT","created_at":"2026-07-05T02:47:43Z"},{"alias_kind":"pith_short_8","alias_value":"G5X6NNMN","created_at":"2026-07-05T02:47:43Z"}],"graph_snapshots":[{"event_id":"sha256:03b1bacf07c4c6298f61155fab62cec05f6abba919aef45bd5715eb564c5c247","target":"graph","created_at":"2026-07-05T02:47:43Z","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/2103.16809/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Emotional voice conversion (EVC) aims to change the emotional state of an utterance while preserving the linguistic content and speaker identity. In this paper, we propose a novel 2-stage training strategy for sequence-to-sequence emotional voice conversion with a limited amount of emotional speech data. We note that the proposed EVC framework leverages text-to-speech (TTS) as they share a common goal that is to generate high-quality expressive voice. In stage 1, we perform style initialization with a multi-speaker TTS corpus, to disentangle speaking style and linguistic content. In stage 2, w","authors_text":"Berrak Sisman, Haizhou Li, Kun Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-31T04:56:14Z","title":"Limited Data Emotional Voice Conversion Leveraging Text-to-Speech: Two-stage Sequence-to-Sequence Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16809","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:ec4c8c04ddf4725e36012f4f291c3fa1ec1fbd90dca2fbf4b67459e5981de1b6","target":"record","created_at":"2026-07-05T02:47:43Z","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":"08a91886d240999ae9ecf70e6522b61195ddc3f78b5182c781f41feedb9a1946","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-31T04:56:14Z","title_canon_sha256":"200d51bbbb54484deaf528a2b9a56aaa1f7281aa77eaf183606ab6e94ccaef0d"},"schema_version":"1.0","source":{"id":"2103.16809","kind":"arxiv","version":2}},"canonical_sha256":"376fe6b58d728bb7c853cc195028f60213845fb83287ea4c91035a8836f9c219","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"376fe6b58d728bb7c853cc195028f60213845fb83287ea4c91035a8836f9c219","first_computed_at":"2026-07-05T02:47:43.681476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:43.681476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7hT15wqpAxdepxDWvi/I5NUYrpPGZpPf2Mh+tNI0OAevbmqHbnlEHgVdtx+IUs54Xb4rMaPT02YhUyIS5xNhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:43.681915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.16809","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec4c8c04ddf4725e36012f4f291c3fa1ec1fbd90dca2fbf4b67459e5981de1b6","sha256:03b1bacf07c4c6298f61155fab62cec05f6abba919aef45bd5715eb564c5c247"],"state_sha256":"d8a190483cfbf10dce8746d0b3628ebc17c09b82a211af1de576484108457def"}