{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X7UGLHN3DFBUBPWRCTN3C7OSCJ","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":"da1a02744c03ca8cfb2f492eb2f1325218f9e95c7daaf6b98435f141f2b39a41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-16T10:04:21Z","title_canon_sha256":"f9cf378e9dea487149534088e1a33b72daec0c98338817ba4d7c26eac54bb93d"},"schema_version":"1.0","source":{"id":"2508.12001","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12001","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12001v3","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12001","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"X7UGLHN3DFBU","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"X7UGLHN3DFBUBPWR","created_at":"2026-05-29T02:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"X7UGLHN3","created_at":"2026-05-29T02:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:6763777cff159ed7b59b7d80965d7a58b209d49585df827022fe73370aad4e45","target":"graph","created_at":"2026-05-29T02:05:35Z","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/2508.12001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current non-autoregressive (NAR) text-to-speech (TTS) systems still struggle to model diverse and speaker-dependent duration variation. We further observe that richer duration variation can increase the synthesis difficulty of existing HiFi-GAN-based vocoders, leading to spectral artifacts and unstable time-frequency structures. To address these issues, we propose FNH-TTS, a VITS-based end-to-end TTS system with Mixture-of-Experts duration modeling and robust vocoder-side synthesis. Specifically, we introduce a Mixture-of-Experts Duration Predictor (MoE-DP) to capture diverse phoneme duration ","authors_text":"Huizhi Liang, Limei Yu, Qingliang Meng, Tian Li, Wei Liang, Yuqing Deng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-16T10:04:21Z","title":"FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12001","kind":"arxiv","version":3},"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":"sha256:1171328b13bdd6e9046364c73f11cbb30e235994c0e33cac3608d0bd38fe0458","target":"record","created_at":"2026-05-29T02:05:35Z","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":"da1a02744c03ca8cfb2f492eb2f1325218f9e95c7daaf6b98435f141f2b39a41","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-16T10:04:21Z","title_canon_sha256":"f9cf378e9dea487149534088e1a33b72daec0c98338817ba4d7c26eac54bb93d"},"schema_version":"1.0","source":{"id":"2508.12001","kind":"arxiv","version":3}},"canonical_sha256":"bfe8659dbb194340bed114dbb17dd21248b5bc2f9a93513e0081af093b0d3f2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfe8659dbb194340bed114dbb17dd21248b5bc2f9a93513e0081af093b0d3f2f","first_computed_at":"2026-05-29T02:05:35.897894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:35.897894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"31o0yhacDKlqsW7DfHXCq/J+UDX8XD+keBr9zGTRcPJSjGcEmT4ZklWWVHALfrtFpeOoSuDAJMXbUU18x3VADw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:35.898389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12001","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1171328b13bdd6e9046364c73f11cbb30e235994c0e33cac3608d0bd38fe0458","sha256:6763777cff159ed7b59b7d80965d7a58b209d49585df827022fe73370aad4e45"],"state_sha256":"cd06c49d7c2cb8ca14f092b7f0877a67bb6ef1cf01a7edbf7b405ffc8d6460fd"}