{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TSMOJEVXKAEXX4V22KU67KV7H3","short_pith_number":"pith:TSMOJEVX","schema_version":"1.0","canonical_sha256":"9c98e492b750097bf2bad2a9efaabf3ee7e25dac917b4698874a09f60ca1bf95","source":{"kind":"arxiv","id":"2305.07243","version":2},"attestation_state":"computed","paper":{"title":"Better speech synthesis through scaling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"James Betker","submitted_at":"2023-05-12T04:19:49Z","abstract_excerpt":"In recent years, the field of image generation has been revolutionized by the application of autoregressive transformers and DDPMs. These approaches model the process of image generation as a step-wise probabilistic processes and leverage large amounts of compute and data to learn the image distribution. This methodology of improving performance need not be confined to images. This paper describes a way to apply advances in the image generative domain to speech synthesis. The result is TorToise -- an expressive, multi-voice text-to-speech system.\n  All model code and trained weights have been "},"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":"2305.07243","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-12T04:19:49Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"7e17cd407c2ba226b2e26d249d5beaef5c0b45518490af5c68b7096cab4bc180","abstract_canon_sha256":"9102c5a06f2b55e39b1cd4994cb8491825bf323776a94c13994d902e97615dd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:20.976464Z","signature_b64":"buh/DTK6JHe8G+oDbuYhERBMG0LTf1xZBSZ0hmvnIN4nBw4fgaLEI9jEJoy3jgNQIlCkPlMxAljr0RQG2rsSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c98e492b750097bf2bad2a9efaabf3ee7e25dac917b4698874a09f60ca1bf95","last_reissued_at":"2026-07-05T06:13:20.976063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:20.976063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Better speech synthesis through scaling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"James Betker","submitted_at":"2023-05-12T04:19:49Z","abstract_excerpt":"In recent years, the field of image generation has been revolutionized by the application of autoregressive transformers and DDPMs. These approaches model the process of image generation as a step-wise probabilistic processes and leverage large amounts of compute and data to learn the image distribution. This methodology of improving performance need not be confined to images. This paper describes a way to apply advances in the image generative domain to speech synthesis. The result is TorToise -- an expressive, multi-voice text-to-speech system.\n  All model code and trained weights have been "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.07243","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/2305.07243/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":"2305.07243","created_at":"2026-07-05T06:13:20.976127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.07243v2","created_at":"2026-07-05T06:13:20.976127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.07243","created_at":"2026-07-05T06:13:20.976127+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSMOJEVXKAEX","created_at":"2026-07-05T06:13:20.976127+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSMOJEVXKAEXX4V2","created_at":"2026-07-05T06:13:20.976127+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSMOJEVX","created_at":"2026-07-05T06:13:20.976127+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25369","citing_title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21343","citing_title":"An Evaluation Framework for Text-to-Speech Voice Reconstruction","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09141","citing_title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2401.09512","citing_title":"MLAAD: The Multi-Language Audio Anti-Spoofing Dataset","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2502.20427","citing_title":"DeePen: Penetration Testing for Audio Deepfake Detection","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05611","citing_title":"X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05611","citing_title":"X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08709","citing_title":"Enhancing Conversational TTS with Cascaded Prompting and ICL-Based Online Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08184","citing_title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3","json":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3.json","graph_json":"https://pith.science/api/pith-number/TSMOJEVXKAEXX4V22KU67KV7H3/graph.json","events_json":"https://pith.science/api/pith-number/TSMOJEVXKAEXX4V22KU67KV7H3/events.json","paper":"https://pith.science/paper/TSMOJEVX"},"agent_actions":{"view_html":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3","download_json":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3.json","view_paper":"https://pith.science/paper/TSMOJEVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.07243&json=true","fetch_graph":"https://pith.science/api/pith-number/TSMOJEVXKAEXX4V22KU67KV7H3/graph.json","fetch_events":"https://pith.science/api/pith-number/TSMOJEVXKAEXX4V22KU67KV7H3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3/action/storage_attestation","attest_author":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3/action/author_attestation","sign_citation":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3/action/citation_signature","submit_replication":"https://pith.science/pith/TSMOJEVXKAEXX4V22KU67KV7H3/action/replication_record"}},"created_at":"2026-07-05T06:13:20.976127+00:00","updated_at":"2026-07-05T06:13:20.976127+00:00"}