{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XJ2O4PBGPK5OPB66CWP3MP4AN7","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":"29a47bfb2c3328d6e85a7aa81c41ecbaa94f8f5c2bb287a19da9a37e8ac271bd","cross_cats_sorted":["cs.AI","cs.HC","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-02T14:20:37Z","title_canon_sha256":"b69cab82f304d39855ccbded48707e3697b7d6782eab905f4077e768e9e3f69e"},"schema_version":"1.0","source":{"id":"2311.01260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01260","created_at":"2026-07-05T07:08:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01260v1","created_at":"2026-07-05T07:08:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01260","created_at":"2026-07-05T07:08:23Z"},{"alias_kind":"pith_short_12","alias_value":"XJ2O4PBGPK5O","created_at":"2026-07-05T07:08:23Z"},{"alias_kind":"pith_short_16","alias_value":"XJ2O4PBGPK5OPB66","created_at":"2026-07-05T07:08:23Z"},{"alias_kind":"pith_short_8","alias_value":"XJ2O4PBG","created_at":"2026-07-05T07:08:23Z"}],"graph_snapshots":[{"event_id":"sha256:b8bbe09496dfc8ed3072141f9a7adc6e468a17add0b9a0745cf12309c49d6415","target":"graph","created_at":"2026-07-05T07:08:23Z","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/2311.01260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive text-to-speech (TTS) aims to synthesize speeches with human-like tones, moods, or even artistic attributes. Recent advancements in expressive TTS empower users with the ability to directly control synthesis style through natural language prompts. However, these methods often require excessive training with a significant amount of style-annotated data, which can be challenging to acquire. Moreover, they may have limited adaptability due to fixed style annotations. In this work, we present FreeStyleTTS (FS-TTS), a controllable expressive TTS model with minimal human annotations. Our a","authors_text":"Hanglei Zhang, Kai Yu, Sen Liu, Xie Chen, Yiwei Guo","cross_cats":["cs.AI","cs.HC","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-02T14:20:37Z","title":"Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01260","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":"sha256:32fc8a2ca9ad2a44f12a7bf59fa0a9866dd8e466065677f586f3cb75ae8ba8c0","target":"record","created_at":"2026-07-05T07:08:23Z","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":"29a47bfb2c3328d6e85a7aa81c41ecbaa94f8f5c2bb287a19da9a37e8ac271bd","cross_cats_sorted":["cs.AI","cs.HC","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-02T14:20:37Z","title_canon_sha256":"b69cab82f304d39855ccbded48707e3697b7d6782eab905f4077e768e9e3f69e"},"schema_version":"1.0","source":{"id":"2311.01260","kind":"arxiv","version":1}},"canonical_sha256":"ba74ee3c267abae787de159fb63f806fd8f459f9c02d050ada9ca9e0bdcd2427","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba74ee3c267abae787de159fb63f806fd8f459f9c02d050ada9ca9e0bdcd2427","first_computed_at":"2026-07-05T07:08:23.237304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:23.237304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TvUBo8EQAguDlBTvdVotA0YUQ1Oc278gcO3cxgA9zWv6ocs/3GDFAOUbxet+1Uu8jiWOqXQOuQYhITgrBZlQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:23.237812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32fc8a2ca9ad2a44f12a7bf59fa0a9866dd8e466065677f586f3cb75ae8ba8c0","sha256:b8bbe09496dfc8ed3072141f9a7adc6e468a17add0b9a0745cf12309c49d6415"],"state_sha256":"d69f4292660f3fe67d31f62f83eaa1983c40b4a0bb2d3dce6779300cb10b47dd"}