{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U3GRAVILG3Y5MTXPZ7JCHZ3F3K","short_pith_number":"pith:U3GRAVIL","schema_version":"1.0","canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","source":{"kind":"arxiv","id":"2606.16417","version":2},"attestation_state":"computed","paper":{"title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Xintong Wang, Ye Wang","submitted_at":"2026-06-15T08:55:28Z","abstract_excerpt":"Accent text-to-speech (TTS) aims to synthesize speech with target accents. Existing accent TTS systems typically rely on a two-stage pipeline that first converts standard phone sequences into accented phone sequences and then synthesizes accented speech. However, such approaches suffer from error accumulation and require paired standard-accented phone sequence data, which is often limited in practice. Moreover, text-based accented phone representations are insufficient to model acoustic accent characteristics such as prosody and rhythm. In this work, we propose Joycent, a diffusion-based accen"},"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":"2606.16417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-15T08:55:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7f87edd3dfe8c60b61c6985c6b47cdced20e5b0f509665cdbc7b40cdd30becf0","abstract_canon_sha256":"7005c476be098f5a2656cdea23f395e42ed9f3c26217ac44c94e0cbe1f81fe94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:56.418678Z","signature_b64":"x7yZtbh+EgCYyJ3kYyOETJ7/5vdtWW8OD243Qw/PygOwFnwqmeJWpgd8HOpevLQMrMi6SX2YbliXiuXfN/PzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6cd10550b36f1d64eefcfd223e765dab2e9fa964dff899c71faa32f2d7737fa","last_reissued_at":"2026-06-19T16:12:56.418287Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:56.418287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Xintong Wang, Ye Wang","submitted_at":"2026-06-15T08:55:28Z","abstract_excerpt":"Accent text-to-speech (TTS) aims to synthesize speech with target accents. Existing accent TTS systems typically rely on a two-stage pipeline that first converts standard phone sequences into accented phone sequences and then synthesizes accented speech. However, such approaches suffer from error accumulation and require paired standard-accented phone sequence data, which is often limited in practice. Moreover, text-based accented phone representations are insufficient to model acoustic accent characteristics such as prosody and rhythm. In this work, we propose Joycent, a diffusion-based accen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16417","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/2606.16417/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":"2606.16417","created_at":"2026-06-19T16:12:56.418364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.16417v2","created_at":"2026-06-19T16:12:56.418364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16417","created_at":"2026-06-19T16:12:56.418364+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3GRAVILG3Y5","created_at":"2026-06-19T16:12:56.418364+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3GRAVILG3Y5MTXP","created_at":"2026-06-19T16:12:56.418364+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3GRAVIL","created_at":"2026-06-19T16:12:56.418364+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/U3GRAVILG3Y5MTXPZ7JCHZ3F3K","json":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K.json","graph_json":"https://pith.science/api/pith-number/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/graph.json","events_json":"https://pith.science/api/pith-number/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/events.json","paper":"https://pith.science/paper/U3GRAVIL"},"agent_actions":{"view_html":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K","download_json":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K.json","view_paper":"https://pith.science/paper/U3GRAVIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.16417&json=true","fetch_graph":"https://pith.science/api/pith-number/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/graph.json","fetch_events":"https://pith.science/api/pith-number/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/action/storage_attestation","attest_author":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/action/author_attestation","sign_citation":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/action/citation_signature","submit_replication":"https://pith.science/pith/U3GRAVILG3Y5MTXPZ7JCHZ3F3K/action/replication_record"}},"created_at":"2026-06-19T16:12:56.418364+00:00","updated_at":"2026-06-19T16:12:56.418364+00:00"}