{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XJ2O4PBGPK5OPB66CWP3MP4AN7","short_pith_number":"pith:XJ2O4PBG","canonical_record":{"source":{"id":"2311.01260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-02T14:20:37Z","cross_cats_sorted":["cs.AI","cs.HC","cs.SD"],"title_canon_sha256":"b69cab82f304d39855ccbded48707e3697b7d6782eab905f4077e768e9e3f69e","abstract_canon_sha256":"29a47bfb2c3328d6e85a7aa81c41ecbaa94f8f5c2bb287a19da9a37e8ac271bd"},"schema_version":"1.0"},"canonical_sha256":"ba74ee3c267abae787de159fb63f806fd8f459f9c02d050ada9ca9e0bdcd2427","source":{"kind":"arxiv","id":"2311.01260","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XJ2O4PBGPK5OPB66CWP3MP4AN7","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01260","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-11-02T14:20:37Z","cross_cats_sorted":["cs.AI","cs.HC","cs.SD"],"title_canon_sha256":"b69cab82f304d39855ccbded48707e3697b7d6782eab905f4077e768e9e3f69e","abstract_canon_sha256":"29a47bfb2c3328d6e85a7aa81c41ecbaa94f8f5c2bb287a19da9a37e8ac271bd"},"schema_version":"1.0"},"canonical_sha256":"ba74ee3c267abae787de159fb63f806fd8f459f9c02d050ada9ca9e0bdcd2427","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:23.237812Z","signature_b64":"TvUBo8EQAguDlBTvdVotA0YUQ1Oc278gcO3cxgA9zWv6ocs/3GDFAOUbxet+1Uu8jiWOqXQOuQYhITgrBZlQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba74ee3c267abae787de159fb63f806fd8f459f9c02d050ada9ca9e0bdcd2427","last_reissued_at":"2026-07-05T07:08:23.237304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:23.237304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01260","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hm1o2i7VhyJC1osAFtTR1pjS2imWNZaRZrHVx5Gn3j4UHxM6dDDt47/v9ierJ8wnXzcaqb1nPToiQTwMWdTCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:02:59.199951Z"},"content_sha256":"32fc8a2ca9ad2a44f12a7bf59fa0a9866dd8e466065677f586f3cb75ae8ba8c0","schema_version":"1.0","event_id":"sha256:32fc8a2ca9ad2a44f12a7bf59fa0a9866dd8e466065677f586f3cb75ae8ba8c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XJ2O4PBGPK5OPB66CWP3MP4AN7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expressive TTS Driven by Natural Language Prompts Using Few Human Annotations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hanglei Zhang, Kai Yu, Sen Liu, Xie Chen, Yiwei Guo","submitted_at":"2023-11-02T14:20:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01260","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.01260/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/OsKtOEwenn+fyC8GgBsSTmVp2w1Zw9yGzY8xw+ty3kzJMeBDhOsZiF8DvBtPzxab4+2GzofPT73H0Rl410eDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:02:59.200480Z"},"content_sha256":"b8bbe09496dfc8ed3072141f9a7adc6e468a17add0b9a0745cf12309c49d6415","schema_version":"1.0","event_id":"sha256:b8bbe09496dfc8ed3072141f9a7adc6e468a17add0b9a0745cf12309c49d6415"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7/bundle.json","state_url":"https://pith.science/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T09:02:59Z","links":{"resolver":"https://pith.science/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7","bundle":"https://pith.science/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7/bundle.json","state":"https://pith.science/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJ2O4PBGPK5OPB66CWP3MP4AN7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uAs7GfHPDaCVD92yFFJVBtT+pJZpK/f0JLGTy7j0R72jwiElOhtW8hEsXqx4JHrDoy0V+zDNzYQnEaHYjpPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:02:59.205027Z","bundle_sha256":"4a81cc89b422c23e90752ebb815bf8981f0e9da00fbc9fbab5d8edf3c13a0327"}}