{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HTGGUKEGERR3AHM6HLI2FAS5GQ","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":"0af1f095eb21a2d3bcf241c13e5e12bcb28574d04e75b62878aabf806c4a35b2","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-14T21:17:58Z","title_canon_sha256":"d3aea9e9ceb5f516e13fee101dceadb40c1eb48f4f7f1df66d388491c5b1e976"},"schema_version":"1.0","source":{"id":"2410.11097","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11097","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11097v2","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11097","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_12","alias_value":"HTGGUKEGERR3","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_16","alias_value":"HTGGUKEGERR3AHM6","created_at":"2026-07-05T10:17:12Z"},{"alias_kind":"pith_short_8","alias_value":"HTGGUKEG","created_at":"2026-07-05T10:17:12Z"}],"graph_snapshots":[{"event_id":"sha256:0b159daa1347624a0c38822e9cf0e46ac72d35e4a3ef99bb99ba518c325cc302","target":"graph","created_at":"2026-07-05T10:17:12Z","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/2410.11097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have demonstrated significant potential in speech synthesis tasks, including text-to-speech (TTS) and voice cloning. However, their iterative denoising processes are computationally intensive, and previous distillation attempts have shown consistent quality degradation. Moreover, existing TTS approaches are limited by non-differentiable components or iterative sampling that prevent true end-to-end optimization with perceptual metrics. We introduce DMOSpeech, a distilled diffusion-based TTS model that uniquely achieves both faster inference and superior performance compared to ","authors_text":"Rithesh Kumar, Yingahao Aaron Li, Zeyu Jin","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-14T21:17:58Z","title":"DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11097","kind":"arxiv","version":2},"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:bca4a7ae191e5f41e92fd5477cf68385cfdf4aff82131dc01ff65e9ac797b8b1","target":"record","created_at":"2026-07-05T10:17:12Z","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":"0af1f095eb21a2d3bcf241c13e5e12bcb28574d04e75b62878aabf806c4a35b2","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-14T21:17:58Z","title_canon_sha256":"d3aea9e9ceb5f516e13fee101dceadb40c1eb48f4f7f1df66d388491c5b1e976"},"schema_version":"1.0","source":{"id":"2410.11097","kind":"arxiv","version":2}},"canonical_sha256":"3ccc6a28862463b01d9e3ad1a2825d342111c37ea0ee263169e12a82a13a8066","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ccc6a28862463b01d9e3ad1a2825d342111c37ea0ee263169e12a82a13a8066","first_computed_at":"2026-07-05T10:17:12.227450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:12.227450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d9s/Hyt5zENv96A7d/irjOzBdzO5cfoD6RWmMQjs6DRyB+ll+lphGKjmL8fACbCOrxVXWTS4UNrBjG2MEeyfDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:12.227941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11097","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bca4a7ae191e5f41e92fd5477cf68385cfdf4aff82131dc01ff65e9ac797b8b1","sha256:0b159daa1347624a0c38822e9cf0e46ac72d35e4a3ef99bb99ba518c325cc302"],"state_sha256":"2b4a52cd6b9f937f9167be8f394390c05fd569a40c384ab4b750c21c7bc872e4"}