{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MPZNHTQUALACNWNGLSUGULKK7J","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":"4c5033cc2992c40fcef81d3477a33b922d11f0972e111133bf42f01b99809044","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-13T07:05:44Z","title_canon_sha256":"058bce22f1d5dc63b813538c45778c73bb5e12370dc55098ffd28a36f7a99ab6"},"schema_version":"1.0","source":{"id":"2207.06000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06000","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06000v1","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06000","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"MPZNHTQUALAC","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"pith_short_16","alias_value":"MPZNHTQUALACNWNG","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"pith_short_8","alias_value":"MPZNHTQU","created_at":"2026-07-05T04:39:53Z"}],"graph_snapshots":[{"event_id":"sha256:e6aec8b0bec5531e817848fc14d4f8e182e91a5e2b6be7dce30fc78d029720aa","target":"graph","created_at":"2026-07-05T04:39:53Z","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/2207.06000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive text-to-speech has shown improved performance in recent years. However, the style control of synthetic speech is often restricted to discrete emotion categories and requires training data recorded by the target speaker in the target style. In many practical situations, users may not have reference speech recorded in target emotion but still be interested in controlling speech style just by typing text description of desired emotional style. In this paper, we propose a text-based interface for emotional style control and cross-speaker style transfer in multi-speaker TTS. We propose t","authors_text":"Suhee Jo, Taesu Kim, Yeongtae Hwang, Yookyung Shin, Younggun Lee","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-13T07:05:44Z","title":"Text-driven Emotional Style Control and Cross-speaker Style Transfer in Neural TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06000","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":"sha256:0273e41c0b43f31e07060030a2e9fd33077e2f2777daba68e36c661e094ae9d8","target":"record","created_at":"2026-07-05T04:39:53Z","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":"4c5033cc2992c40fcef81d3477a33b922d11f0972e111133bf42f01b99809044","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-13T07:05:44Z","title_canon_sha256":"058bce22f1d5dc63b813538c45778c73bb5e12370dc55098ffd28a36f7a99ab6"},"schema_version":"1.0","source":{"id":"2207.06000","kind":"arxiv","version":1}},"canonical_sha256":"63f2d3ce1402c026d9a65ca86a2d4afa6b63b226f5777a559f408198d9a7e2d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63f2d3ce1402c026d9a65ca86a2d4afa6b63b226f5777a559f408198d9a7e2d2","first_computed_at":"2026-07-05T04:39:53.637493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:53.637493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Rt15CtjYsVX39w8AU2UFqPJJbnMdaQ8oLk55wadIRAcQq3wYUABYOeDwpwIGN0PnwuyLjZTxowxHIX7o1z9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:53.637932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0273e41c0b43f31e07060030a2e9fd33077e2f2777daba68e36c661e094ae9d8","sha256:e6aec8b0bec5531e817848fc14d4f8e182e91a5e2b6be7dce30fc78d029720aa"],"state_sha256":"1335db8c75c3890364ca10961053bd177deacde557a767cf153cc04781559c16"}