{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:73FN3DFN6FAXCWAC4U7MRHUDVB","short_pith_number":"pith:73FN3DFN","schema_version":"1.0","canonical_sha256":"fecadd8cadf141715802e53ec89e83a8670669f054d148a4cb0fd72a36f3813d","source":{"kind":"arxiv","id":"2505.19931","version":2},"attestation_state":"computed","paper":{"title":"Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kai Yu, Qixi Zheng, Xiaofei Wang, Xie Chen, Yushen Chen, Zhikang Niu, Ziyang Ma","submitted_at":"2025-05-26T12:58:27Z","abstract_excerpt":"Flow-matching-based text-to-speech (TTS) models, such as Voicebox, E2 TTS, and F5-TTS, have attracted significant attention in recent years. These models require multiple sampling steps to reconstruct speech from noise, making inference speed a key challenge. Reducing the number of sampling steps can greatly improve inference efficiency. To this end, we introduce Fast F5-TTS, a training-free approach to accelerate the inference of flow-matching-based TTS models. By inspecting the sampling trajectory of F5-TTS, we identify redundant steps and propose Empirically Pruned Step Sampling (EPSS), a n"},"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":"2505.19931","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T12:58:27Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3245e2bcac41edad960693ed7aa9acb68f33fcc546c7de1556a32dfc8705ceeb","abstract_canon_sha256":"70fbec19af5c7672157c6422445efe094ad56c165317f37f7fcf943fff816d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:47.059652Z","signature_b64":"vUBogSfmfkoRsTCuQY3NCkUKx7eimDXeUJ9X2uG8EgfgyRIQ+17WbljROEUvsnjbcWKcarPrks+TV0QVJ35mCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fecadd8cadf141715802e53ec89e83a8670669f054d148a4cb0fd72a36f3813d","last_reissued_at":"2026-07-05T11:15:47.059128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:47.059128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kai Yu, Qixi Zheng, Xiaofei Wang, Xie Chen, Yushen Chen, Zhikang Niu, Ziyang Ma","submitted_at":"2025-05-26T12:58:27Z","abstract_excerpt":"Flow-matching-based text-to-speech (TTS) models, such as Voicebox, E2 TTS, and F5-TTS, have attracted significant attention in recent years. These models require multiple sampling steps to reconstruct speech from noise, making inference speed a key challenge. Reducing the number of sampling steps can greatly improve inference efficiency. To this end, we introduce Fast F5-TTS, a training-free approach to accelerate the inference of flow-matching-based TTS models. By inspecting the sampling trajectory of F5-TTS, we identify redundant steps and propose Empirically Pruned Step Sampling (EPSS), a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19931","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/2505.19931/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":"2505.19931","created_at":"2026-07-05T11:15:47.059206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19931v2","created_at":"2026-07-05T11:15:47.059206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19931","created_at":"2026-07-05T11:15:47.059206+00:00"},{"alias_kind":"pith_short_12","alias_value":"73FN3DFN6FAX","created_at":"2026-07-05T11:15:47.059206+00:00"},{"alias_kind":"pith_short_16","alias_value":"73FN3DFN6FAXCWAC","created_at":"2026-07-05T11:15:47.059206+00:00"},{"alias_kind":"pith_short_8","alias_value":"73FN3DFN","created_at":"2026-07-05T11:15:47.059206+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/73FN3DFN6FAXCWAC4U7MRHUDVB","json":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB.json","graph_json":"https://pith.science/api/pith-number/73FN3DFN6FAXCWAC4U7MRHUDVB/graph.json","events_json":"https://pith.science/api/pith-number/73FN3DFN6FAXCWAC4U7MRHUDVB/events.json","paper":"https://pith.science/paper/73FN3DFN"},"agent_actions":{"view_html":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB","download_json":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB.json","view_paper":"https://pith.science/paper/73FN3DFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19931&json=true","fetch_graph":"https://pith.science/api/pith-number/73FN3DFN6FAXCWAC4U7MRHUDVB/graph.json","fetch_events":"https://pith.science/api/pith-number/73FN3DFN6FAXCWAC4U7MRHUDVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB/action/storage_attestation","attest_author":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB/action/author_attestation","sign_citation":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB/action/citation_signature","submit_replication":"https://pith.science/pith/73FN3DFN6FAXCWAC4U7MRHUDVB/action/replication_record"}},"created_at":"2026-07-05T11:15:47.059206+00:00","updated_at":"2026-07-05T11:15:47.059206+00:00"}