{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TSVVDHV2MZQKY77CTASRZKONXY","short_pith_number":"pith:TSVVDHV2","schema_version":"1.0","canonical_sha256":"9cab519eba6660ac7fe298251ca9cdbe2930de0bbd1161f2390f1beb6e80fd56","source":{"kind":"arxiv","id":"2309.10740","version":3},"attestation_state":"computed","paper":{"title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dung Tran, Kazuhito Koishida, Somayeh Sojoudi, Trung Dang, Yatong Bai","submitted_at":"2023-09-19T16:36:33Z","abstract_excerpt":"Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we introduce ConsistencyTTA, a framework requiring only a single non-autoregressive network query, thereby accelerating TTA by hundreds of times. We achieve so by proposing \"CFG-aware latent consistency model,\" which adapts consistency generation into a latent space and incorporates classifier-free guidance (CFG) into model training. Moreover, unlike diffusion mod"},"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":"2309.10740","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-19T16:36:33Z","cross_cats_sorted":["cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"f2438bd723bd246f38d2259e67011eebf1ab1e0b963b0aa11590cec34916a1dd","abstract_canon_sha256":"6b7430b2e8b50cfe784b3a000aafb2c190df6f507b5fd99934c56941c1fe00dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:36.925200Z","signature_b64":"8LNtRVh1OXSb+aZ7bIzSoZos7Z4uB2xb4NfBe++mcxTuv2YtsYFIVxHaAQ5xxspSgAPlNWosLDQsyk530fjxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cab519eba6660ac7fe298251ca9cdbe2930de0bbd1161f2390f1beb6e80fd56","last_reissued_at":"2026-07-05T08:35:36.924705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:36.924705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dung Tran, Kazuhito Koishida, Somayeh Sojoudi, Trung Dang, Yatong Bai","submitted_at":"2023-09-19T16:36:33Z","abstract_excerpt":"Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we introduce ConsistencyTTA, a framework requiring only a single non-autoregressive network query, thereby accelerating TTA by hundreds of times. We achieve so by proposing \"CFG-aware latent consistency model,\" which adapts consistency generation into a latent space and incorporates classifier-free guidance (CFG) into model training. Moreover, unlike diffusion mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10740","kind":"arxiv","version":3},"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/2309.10740/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":"2309.10740","created_at":"2026-07-05T08:35:36.924768+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10740v3","created_at":"2026-07-05T08:35:36.924768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10740","created_at":"2026-07-05T08:35:36.924768+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSVVDHV2MZQK","created_at":"2026-07-05T08:35:36.924768+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSVVDHV2MZQKY77C","created_at":"2026-07-05T08:35:36.924768+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSVVDHV2","created_at":"2026-07-05T08:35:36.924768+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24307","citing_title":"Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00329","citing_title":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY","json":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY.json","graph_json":"https://pith.science/api/pith-number/TSVVDHV2MZQKY77CTASRZKONXY/graph.json","events_json":"https://pith.science/api/pith-number/TSVVDHV2MZQKY77CTASRZKONXY/events.json","paper":"https://pith.science/paper/TSVVDHV2"},"agent_actions":{"view_html":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY","download_json":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY.json","view_paper":"https://pith.science/paper/TSVVDHV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10740&json=true","fetch_graph":"https://pith.science/api/pith-number/TSVVDHV2MZQKY77CTASRZKONXY/graph.json","fetch_events":"https://pith.science/api/pith-number/TSVVDHV2MZQKY77CTASRZKONXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY/action/storage_attestation","attest_author":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY/action/author_attestation","sign_citation":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY/action/citation_signature","submit_replication":"https://pith.science/pith/TSVVDHV2MZQKY77CTASRZKONXY/action/replication_record"}},"created_at":"2026-07-05T08:35:36.924768+00:00","updated_at":"2026-07-05T08:35:36.924768+00:00"}