{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5SCWZ6Z7XM27GZ6TW2WEHG6GNR","short_pith_number":"pith:5SCWZ6Z7","schema_version":"1.0","canonical_sha256":"ec856cfb3fbb35f367d3b6ac439bc66c58a6169896b45d1fd7e743b6de9a029f","source":{"kind":"arxiv","id":"2505.05159","version":3},"attestation_state":"computed","paper":{"title":"FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dake Guo, He Wang, Jin Xu, Lei Xie, Linhan Ma","submitted_at":"2025-05-08T11:55:19Z","abstract_excerpt":"Current speech generation research can be categorized into two primary classes: non-autoregressive and autoregressive. The fundamental distinction between these approaches lies in the duration prediction strategy employed for predictable-length sequences. The NAR methods ensure stability in speech generation by explicitly and independently modeling the duration of each phonetic unit. Conversely, AR methods employ an autoregressive paradigm to predict the compressed speech token by implicitly modeling duration with Markov properties. Although this approach improves prosody, it does not provide "},"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":"2505.05159","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-08T11:55:19Z","cross_cats_sorted":[],"title_canon_sha256":"da0f4c55f67d071be278122d4fe1f2f93a7902f22fbe712e1aea5020af35d67d","abstract_canon_sha256":"0e8072598463947638abd25bde4a789a85b485d02d081aa7d26b8b0ab3376beb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:24.216967Z","signature_b64":"FuDikRX8gXXljxFlJ0Ubj5I9pBfg77N3qG7Xrw6FTjgDQNEw+vyNYeUTIUbYw3jbqrWG4baBdIihv/CLDaiTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec856cfb3fbb35f367d3b6ac439bc66c58a6169896b45d1fd7e743b6de9a029f","last_reissued_at":"2026-07-05T11:03:24.216487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:24.216487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlexSpeech: Towards Stable, Controllable and Expressive Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dake Guo, He Wang, Jin Xu, Lei Xie, Linhan Ma","submitted_at":"2025-05-08T11:55:19Z","abstract_excerpt":"Current speech generation research can be categorized into two primary classes: non-autoregressive and autoregressive. The fundamental distinction between these approaches lies in the duration prediction strategy employed for predictable-length sequences. The NAR methods ensure stability in speech generation by explicitly and independently modeling the duration of each phonetic unit. Conversely, AR methods employ an autoregressive paradigm to predict the compressed speech token by implicitly modeling duration with Markov properties. Although this approach improves prosody, it does not provide "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05159","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/2505.05159/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":"2505.05159","created_at":"2026-07-05T11:03:24.216552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05159v3","created_at":"2026-07-05T11:03:24.216552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05159","created_at":"2026-07-05T11:03:24.216552+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SCWZ6Z7XM27","created_at":"2026-07-05T11:03:24.216552+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SCWZ6Z7XM27GZ6T","created_at":"2026-07-05T11:03:24.216552+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SCWZ6Z7","created_at":"2026-07-05T11:03:24.216552+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/5SCWZ6Z7XM27GZ6TW2WEHG6GNR","json":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR.json","graph_json":"https://pith.science/api/pith-number/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/graph.json","events_json":"https://pith.science/api/pith-number/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/events.json","paper":"https://pith.science/paper/5SCWZ6Z7"},"agent_actions":{"view_html":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR","download_json":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR.json","view_paper":"https://pith.science/paper/5SCWZ6Z7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05159&json=true","fetch_graph":"https://pith.science/api/pith-number/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/graph.json","fetch_events":"https://pith.science/api/pith-number/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/action/storage_attestation","attest_author":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/action/author_attestation","sign_citation":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/action/citation_signature","submit_replication":"https://pith.science/pith/5SCWZ6Z7XM27GZ6TW2WEHG6GNR/action/replication_record"}},"created_at":"2026-07-05T11:03:24.216552+00:00","updated_at":"2026-07-05T11:03:24.216552+00:00"}