{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HTGGUKEGERR3AHM6HLI2FAS5GQ","short_pith_number":"pith:HTGGUKEG","schema_version":"1.0","canonical_sha256":"3ccc6a28862463b01d9e3ad1a2825d342111c37ea0ee263169e12a82a13a8066","source":{"kind":"arxiv","id":"2410.11097","version":2},"attestation_state":"computed","paper":{"title":"DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Rithesh Kumar, Yingahao Aaron Li, Zeyu Jin","submitted_at":"2024-10-14T21:17:58Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.11097","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-14T21:17:58Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"d3aea9e9ceb5f516e13fee101dceadb40c1eb48f4f7f1df66d388491c5b1e976","abstract_canon_sha256":"0af1f095eb21a2d3bcf241c13e5e12bcb28574d04e75b62878aabf806c4a35b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:12.227941Z","signature_b64":"d9s/Hyt5zENv96A7d/irjOzBdzO5cfoD6RWmMQjs6DRyB+ll+lphGKjmL8fACbCOrxVXWTS4UNrBjG2MEeyfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ccc6a28862463b01d9e3ad1a2825d342111c37ea0ee263169e12a82a13a8066","last_reissued_at":"2026-07-05T10:17:12.227450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:12.227450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Rithesh Kumar, Yingahao Aaron Li, Zeyu Jin","submitted_at":"2024-10-14T21:17:58Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11097","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.11097/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.11097","created_at":"2026-07-05T10:17:12.227506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11097v2","created_at":"2026-07-05T10:17:12.227506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11097","created_at":"2026-07-05T10:17:12.227506+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTGGUKEGERR3","created_at":"2026-07-05T10:17:12.227506+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTGGUKEGERR3AHM6","created_at":"2026-07-05T10:17:12.227506+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTGGUKEG","created_at":"2026-07-05T10:17:12.227506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ","json":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ.json","graph_json":"https://pith.science/api/pith-number/HTGGUKEGERR3AHM6HLI2FAS5GQ/graph.json","events_json":"https://pith.science/api/pith-number/HTGGUKEGERR3AHM6HLI2FAS5GQ/events.json","paper":"https://pith.science/paper/HTGGUKEG"},"agent_actions":{"view_html":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ","download_json":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ.json","view_paper":"https://pith.science/paper/HTGGUKEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11097&json=true","fetch_graph":"https://pith.science/api/pith-number/HTGGUKEGERR3AHM6HLI2FAS5GQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HTGGUKEGERR3AHM6HLI2FAS5GQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ/action/storage_attestation","attest_author":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ/action/author_attestation","sign_citation":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ/action/citation_signature","submit_replication":"https://pith.science/pith/HTGGUKEGERR3AHM6HLI2FAS5GQ/action/replication_record"}},"created_at":"2026-07-05T10:17:12.227506+00:00","updated_at":"2026-07-05T10:17:12.227506+00:00"}