{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5Q2O2GXL3Y2PN3EDGLDAHDSIIY","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":"9924de96a622449cdf292f15877a0b00d3101c5ca53c0a7863f720b092cf94c8","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-18T13:42:38Z","title_canon_sha256":"c27323d85e701b2d96beafa1d93a48712a4ae4521716ff078c89344a298074e7"},"schema_version":"1.0","source":{"id":"2407.13509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13509","created_at":"2026-07-05T08:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13509v1","created_at":"2026-07-05T08:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13509","created_at":"2026-07-05T08:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"5Q2O2GXL3Y2P","created_at":"2026-07-05T08:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"5Q2O2GXL3Y2PN3ED","created_at":"2026-07-05T08:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"5Q2O2GXL","created_at":"2026-07-05T08:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:51bcf937c75b6f218c276caf0ab248ce155032942e6c37513c06d481a463c364","target":"graph","created_at":"2026-07-05T08:45:39Z","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/2407.13509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spontaneous style speech synthesis, which aims to generate human-like speech, often encounters challenges due to the scarcity of high-quality data and limitations in model capabilities. Recent language model-based TTS systems can be trained on large, diverse, and low-quality speech datasets, resulting in highly natural synthesized speech. However, they are limited by the difficulty of simulating various spontaneous behaviors and capturing prosody variations in spontaneous speech. In this paper, we propose a novel spontaneous speech synthesis system based on language models. We systematically c","authors_text":"Helen Meng, Peiji Yang, Weiqin Li, Xixin Wu, Yicheng Zhong, Yixuan Zhou, Zhisheng Wang, Zhiyong Wu","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-18T13:42:38Z","title":"Spontaneous Style Text-to-Speech Synthesis with Controllable Spontaneous Behaviors Based on Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13509","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":"sha256:59a5b1c9951a50a0923c154bb4c987b34f0c0a8fd7d8a49d3dc8ff2e1b7c327d","target":"record","created_at":"2026-07-05T08:45:39Z","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":"9924de96a622449cdf292f15877a0b00d3101c5ca53c0a7863f720b092cf94c8","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-18T13:42:38Z","title_canon_sha256":"c27323d85e701b2d96beafa1d93a48712a4ae4521716ff078c89344a298074e7"},"schema_version":"1.0","source":{"id":"2407.13509","kind":"arxiv","version":1}},"canonical_sha256":"ec34ed1aebde34f6ec8332c6038e4846086185543d17696a21df1712952e0f49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec34ed1aebde34f6ec8332c6038e4846086185543d17696a21df1712952e0f49","first_computed_at":"2026-07-05T08:45:39.914990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:39.914990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3/d3DJbMK7hvc+zsV3ZXBHF5AvKCs5w7MwgEz33DO7fIDtcfnyw7rjvw71KEVmBpcyjFM47O7X0GqKZcIdn3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:39.915461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59a5b1c9951a50a0923c154bb4c987b34f0c0a8fd7d8a49d3dc8ff2e1b7c327d","sha256:51bcf937c75b6f218c276caf0ab248ce155032942e6c37513c06d481a463c364"],"state_sha256":"6e6b7690a88051f8ffa92c66e76975f05a0048097b88cfa96bbf2fbf2ee290a1"}