{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ISTXDV4F3WF7YZMOOJ45BHHSSI","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":"ce9bca8041eda64a7c793a4c43217754852faab64e853b7cf045841fb488a6bf","cross_cats_sorted":["cs.AI","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T08:51:50Z","title_canon_sha256":"125e03c6aabf543819b93c0557c3191fbb983d7f29c50d522df0128a7e35f159"},"schema_version":"1.0","source":{"id":"2406.05699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05699","created_at":"2026-07-05T08:29:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05699v1","created_at":"2026-07-05T08:29:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05699","created_at":"2026-07-05T08:29:32Z"},{"alias_kind":"pith_short_12","alias_value":"ISTXDV4F3WF7","created_at":"2026-07-05T08:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"ISTXDV4F3WF7YZMO","created_at":"2026-07-05T08:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"ISTXDV4F","created_at":"2026-07-05T08:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:1a0b60f74045d2f268cb418f9e99c9711810770e0a4d16604709782e932def69","target":"graph","created_at":"2026-07-05T08:29:32Z","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/2406.05699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, zero-shot text-to-speech (TTS) systems, capable of synthesizing any speaker's voice from a short audio prompt, have made rapid advancements. However, the quality of the generated speech significantly deteriorates when the audio prompt contains noise, and limited research has been conducted to address this issue. In this paper, we explored various strategies to enhance the quality of audio generated from noisy audio prompts within the context of flow-matching-based zero-shot TTS. Our investigation includes comprehensive training strategies: unsupervised pre-training with masked speech","authors_text":"Hemin Yang, Jinyu Li, Jinzhu Li, Manthan Thakker, Min Tang, Naoyuki Kanda, Sefik Emre Eskimez, Sheng Zhao, Xiaofei Wang, Yufei Xia, Zirun Zhu","cross_cats":["cs.AI","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T08:51:50Z","title":"An Investigation of Noise Robustness for Flow-Matching-Based Zero-Shot TTS"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05699","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":"sha256:5e7be0bd5c5509976f7fc2b9ad4c87737901e1bc5629ec8e673200cf51bf7133","target":"record","created_at":"2026-07-05T08:29:32Z","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":"ce9bca8041eda64a7c793a4c43217754852faab64e853b7cf045841fb488a6bf","cross_cats_sorted":["cs.AI","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T08:51:50Z","title_canon_sha256":"125e03c6aabf543819b93c0557c3191fbb983d7f29c50d522df0128a7e35f159"},"schema_version":"1.0","source":{"id":"2406.05699","kind":"arxiv","version":1}},"canonical_sha256":"44a771d785dd8bfc658e7279d09cf292224aff2db09499b15141595700c31614","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44a771d785dd8bfc658e7279d09cf292224aff2db09499b15141595700c31614","first_computed_at":"2026-07-05T08:29:32.493311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:32.493311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gGvIZmmUehfuQUvIxXvHR028u3Lbm5FGzDHMVR0+ZmGSmrTHj14wwW7iIvoutkmwNfS1ym73zHkIk7atzkiQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:32.493784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e7be0bd5c5509976f7fc2b9ad4c87737901e1bc5629ec8e673200cf51bf7133","sha256:1a0b60f74045d2f268cb418f9e99c9711810770e0a4d16604709782e932def69"],"state_sha256":"ec78f7042878329b029c85f5045d6a9163739037b2754dcf5a1965151795e572"}