{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4CWPP5BKE3ITMTYUR7EKZ2O3UF","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":"f8e68871dceb02feba4c54c38a5a6e0c4c78240f25221a2cb34f7ece415c427d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-14T16:53:39Z","title_canon_sha256":"3754115b5cdebad4f10c82248e03397ffaf4cee00d01f63cdfa69c3cd317c818"},"schema_version":"1.0","source":{"id":"2506.12570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12570","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12570v1","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12570","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_12","alias_value":"4CWPP5BKE3IT","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_16","alias_value":"4CWPP5BKE3ITMTYU","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_8","alias_value":"4CWPP5BK","created_at":"2026-07-05T11:21:55Z"}],"graph_snapshots":[{"event_id":"sha256:a2d3c1cb98963128f54c2807bfe3fe8c971b359bd1b598efd473df2b08e3fe0f","target":"graph","created_at":"2026-07-05T11:21:55Z","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/2506.12570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in zero-shot text-to-speech (TTS) synthesis have achieved high-quality speech generation for unseen speakers, but most systems remain unsuitable for real-time applications because of their offline design. Current streaming TTS paradigms often rely on multi-stage pipelines and discrete representations, leading to increased computational cost and suboptimal system performance. In this work, we propose StreamMel, a pioneering single-stage streaming TTS framework that models continuous mel-spectrograms. By interleaving text tokens with acoustic frames, StreamMel enables low-latency","authors_text":"Haoqin Sun, Hui Wang, Jiaming Zhou, Jinyu Li, Lingwei Meng, Shujie Liu, Yan Lu, Yanqing Liu, Yifan Yang, Yong Qin","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-14T16:53:39Z","title":"StreamMel: Real-Time Zero-shot Text-to-Speech via Interleaved Continuous Autoregressive Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12570","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":"sha256:4ad04ffc4a3cd7018e020ac65437a7b9e2168bbec8c2ab79caa27001048bec24","target":"record","created_at":"2026-07-05T11:21:55Z","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":"f8e68871dceb02feba4c54c38a5a6e0c4c78240f25221a2cb34f7ece415c427d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-14T16:53:39Z","title_canon_sha256":"3754115b5cdebad4f10c82248e03397ffaf4cee00d01f63cdfa69c3cd317c818"},"schema_version":"1.0","source":{"id":"2506.12570","kind":"arxiv","version":1}},"canonical_sha256":"e0acf7f42a26d1364f148fc8ace9dba15892fc894572995117bc1ee3b5a2fdf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0acf7f42a26d1364f148fc8ace9dba15892fc894572995117bc1ee3b5a2fdf6","first_computed_at":"2026-07-05T11:21:55.548329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:55.548329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u78o6a/YMw+uiUA/fiOIPbrwtIsP4diHsHm4lNjgeEqNOFKbHXEP7InE5H7eDQYhU3DNDnT9WCLp0r9Py9pgAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:55.548817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ad04ffc4a3cd7018e020ac65437a7b9e2168bbec8c2ab79caa27001048bec24","sha256:a2d3c1cb98963128f54c2807bfe3fe8c971b359bd1b598efd473df2b08e3fe0f"],"state_sha256":"12805ade5064b172bd8d367d8cf885aac65367e04efdcd17390e3996ce8be73a"}