{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NVWIO4AVQHTI56CMVRDZ45HN4E","short_pith_number":"pith:NVWIO4AV","schema_version":"1.0","canonical_sha256":"6d6c87701581e68ef84cac479e74ede108907c9ffb1ffc26132bfe78ed2f07a8","source":{"kind":"arxiv","id":"2309.06787","version":1},"attestation_state":"computed","paper":{"title":"DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Qiulin Li, Qun Yang, Sixing Liu, Zhichao Wu","submitted_at":"2023-09-13T08:22:38Z","abstract_excerpt":"In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion Model with Contrastive Learning for Text-to-Speech Generation(DCTTS). The following contributions are made by DCTTS: 1) The TTS diffusion model based on discrete space significantly lowers the computational consumption of the diffusion model and improves sampling speed; 2) The contrastive learning method based on discrete space is used to enhance the alignment"},"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":"2309.06787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T08:22:38Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1bcecbeefbcd9ed1f5d61fbac2bb5836a17c0cbbfad32ca59dd8dc5bfb06744e","abstract_canon_sha256":"5bec6164ac77000523a021fedfb4af1d368bb3bf7f62b14988a2d7339a39c191"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:22.426021Z","signature_b64":"hfVtS+r2sEb+YoOLKcusa3QoVf5EhletWb2HdtdyTLWAEfG12PMi23Kq2BpLLq44Kp4s8DxemFGYi+Y6X2uSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d6c87701581e68ef84cac479e74ede108907c9ffb1ffc26132bfe78ed2f07a8","last_reissued_at":"2026-07-05T06:50:22.425603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:22.425603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCTTS: Discrete Diffusion Model with Contrastive Learning for Text-to-speech Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Qiulin Li, Qun Yang, Sixing Liu, Zhichao Wu","submitted_at":"2023-09-13T08:22:38Z","abstract_excerpt":"In the Text-to-speech(TTS) task, the latent diffusion model has excellent fidelity and generalization, but its expensive resource consumption and slow inference speed have always been a challenging. This paper proposes Discrete Diffusion Model with Contrastive Learning for Text-to-Speech Generation(DCTTS). The following contributions are made by DCTTS: 1) The TTS diffusion model based on discrete space significantly lowers the computational consumption of the diffusion model and improves sampling speed; 2) The contrastive learning method based on discrete space is used to enhance the alignment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06787","kind":"arxiv","version":1},"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/2309.06787/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":"2309.06787","created_at":"2026-07-05T06:50:22.425668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06787v1","created_at":"2026-07-05T06:50:22.425668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06787","created_at":"2026-07-05T06:50:22.425668+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVWIO4AVQHTI","created_at":"2026-07-05T06:50:22.425668+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVWIO4AVQHTI56CM","created_at":"2026-07-05T06:50:22.425668+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVWIO4AV","created_at":"2026-07-05T06:50:22.425668+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/NVWIO4AVQHTI56CMVRDZ45HN4E","json":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E.json","graph_json":"https://pith.science/api/pith-number/NVWIO4AVQHTI56CMVRDZ45HN4E/graph.json","events_json":"https://pith.science/api/pith-number/NVWIO4AVQHTI56CMVRDZ45HN4E/events.json","paper":"https://pith.science/paper/NVWIO4AV"},"agent_actions":{"view_html":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E","download_json":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E.json","view_paper":"https://pith.science/paper/NVWIO4AV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06787&json=true","fetch_graph":"https://pith.science/api/pith-number/NVWIO4AVQHTI56CMVRDZ45HN4E/graph.json","fetch_events":"https://pith.science/api/pith-number/NVWIO4AVQHTI56CMVRDZ45HN4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E/action/storage_attestation","attest_author":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E/action/author_attestation","sign_citation":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E/action/citation_signature","submit_replication":"https://pith.science/pith/NVWIO4AVQHTI56CMVRDZ45HN4E/action/replication_record"}},"created_at":"2026-07-05T06:50:22.425668+00:00","updated_at":"2026-07-05T06:50:22.425668+00:00"}