{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KS6C2BNLTGRVCA6YHKDVXGSZMY","short_pith_number":"pith:KS6C2BNL","schema_version":"1.0","canonical_sha256":"54bc2d05ab99a35103d83a875b9a596606bc0541443e76ba1f0bf42da805167b","source":{"kind":"arxiv","id":"2408.13893","version":2},"attestation_state":"computed","paper":{"title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dading Chong, Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Songxiang Liu, Xixin Wu, Yuanyuan Wang","submitted_at":"2024-08-25T17:07:39Z","abstract_excerpt":"Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (\\textit{e.g.}, VALL-E) or Non-auto-regressive (NAR) based models (\\textit{e.g.}, NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models ne"},"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":"2408.13893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-25T17:07:39Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"9186253f34d90ba3983561da2aec74dfa2541cefc83ce894c375b33ffb65d4a7","abstract_canon_sha256":"2fb3bee1e8d6183fbd4acca54c8bded5e33afb9d9ed99c0de7ac35fedd08b1aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:07.965278Z","signature_b64":"R+oyZVOTt0iJzUjoLpcekNiVV/v00Kb0KJNrH+niS/Juur7o7gAEohdwTgrcW1Jyw6ZdHaRHw74UE+09xH/ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54bc2d05ab99a35103d83a875b9a596606bc0541443e76ba1f0bf42da805167b","last_reissued_at":"2026-07-05T09:00:07.964771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:07.964771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dading Chong, Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Songxiang Liu, Xixin Wu, Yuanyuan Wang","submitted_at":"2024-08-25T17:07:39Z","abstract_excerpt":"Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (\\textit{e.g.}, VALL-E) or Non-auto-regressive (NAR) based models (\\textit{e.g.}, NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13893","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/2408.13893/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":"2408.13893","created_at":"2026-07-05T09:00:07.964832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13893v2","created_at":"2026-07-05T09:00:07.964832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13893","created_at":"2026-07-05T09:00:07.964832+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS6C2BNLTGRV","created_at":"2026-07-05T09:00:07.964832+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS6C2BNLTGRVCA6Y","created_at":"2026-07-05T09:00:07.964832+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS6C2BNL","created_at":"2026-07-05T09:00:07.964832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14988","citing_title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY","json":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY.json","graph_json":"https://pith.science/api/pith-number/KS6C2BNLTGRVCA6YHKDVXGSZMY/graph.json","events_json":"https://pith.science/api/pith-number/KS6C2BNLTGRVCA6YHKDVXGSZMY/events.json","paper":"https://pith.science/paper/KS6C2BNL"},"agent_actions":{"view_html":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY","download_json":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY.json","view_paper":"https://pith.science/paper/KS6C2BNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13893&json=true","fetch_graph":"https://pith.science/api/pith-number/KS6C2BNLTGRVCA6YHKDVXGSZMY/graph.json","fetch_events":"https://pith.science/api/pith-number/KS6C2BNLTGRVCA6YHKDVXGSZMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY/action/storage_attestation","attest_author":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY/action/author_attestation","sign_citation":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY/action/citation_signature","submit_replication":"https://pith.science/pith/KS6C2BNLTGRVCA6YHKDVXGSZMY/action/replication_record"}},"created_at":"2026-07-05T09:00:07.964832+00:00","updated_at":"2026-07-05T09:00:07.964832+00:00"}