{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:76LS5QBDKFUCEY4ZEY6AAURAEG","short_pith_number":"pith:76LS5QBD","schema_version":"1.0","canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","source":{"kind":"arxiv","id":"2506.02997","version":1},"attestation_state":"computed","paper":{"title":"Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chunlei Zhang, Dong Yu, Hangting Chen, Yongqi Wang, Zhou Zhao","submitted_at":"2025-06-03T15:31:16Z","abstract_excerpt":"Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized masked-autoencoded style-rich representation as an intermediary. In the first stage, an autoregressive transformer is used for the conditional generation of these style-rich tokens from text and control signals. The second stage generates codec tokens from both text and sampled style-rich tokens. Experiments show that training the first-stage model on exten"},"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":"2506.02997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-06-03T15:31:16Z","cross_cats_sorted":[],"title_canon_sha256":"c60854e35711fcc916a12bb9c5c593265cde7206b133936d05cc6e6731994846","abstract_canon_sha256":"85687c15bd2f6f64049e6da800137dde701ad942246c2edd2f45672490553ebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:13.129091Z","signature_b64":"rNhZskCC/wneBNwEpRZN71C/7w5ZORbXpU2yMAkA0ZM1D9DTzmgz1nuhFhtz5r194/gV36eb73/7vjtvfZDmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff972ec0235168226399263c0052202190567820b1abcbe2a54cbb3f98d2217b","last_reissued_at":"2026-07-05T11:15:13.128666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:13.128666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Chunlei Zhang, Dong Yu, Hangting Chen, Yongqi Wang, Zhou Zhao","submitted_at":"2025-06-03T15:31:16Z","abstract_excerpt":"Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized masked-autoencoded style-rich representation as an intermediary. In the first stage, an autoregressive transformer is used for the conditional generation of these style-rich tokens from text and control signals. The second stage generates codec tokens from both text and sampled style-rich tokens. Experiments show that training the first-stage model on exten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02997","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/2506.02997/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":"2506.02997","created_at":"2026-07-05T11:15:13.128729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02997v1","created_at":"2026-07-05T11:15:13.128729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02997","created_at":"2026-07-05T11:15:13.128729+00:00"},{"alias_kind":"pith_short_12","alias_value":"76LS5QBDKFUC","created_at":"2026-07-05T11:15:13.128729+00:00"},{"alias_kind":"pith_short_16","alias_value":"76LS5QBDKFUCEY4Z","created_at":"2026-07-05T11:15:13.128729+00:00"},{"alias_kind":"pith_short_8","alias_value":"76LS5QBD","created_at":"2026-07-05T11:15:13.128729+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/76LS5QBDKFUCEY4ZEY6AAURAEG","json":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG.json","graph_json":"https://pith.science/api/pith-number/76LS5QBDKFUCEY4ZEY6AAURAEG/graph.json","events_json":"https://pith.science/api/pith-number/76LS5QBDKFUCEY4ZEY6AAURAEG/events.json","paper":"https://pith.science/paper/76LS5QBD"},"agent_actions":{"view_html":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG","download_json":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG.json","view_paper":"https://pith.science/paper/76LS5QBD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02997&json=true","fetch_graph":"https://pith.science/api/pith-number/76LS5QBDKFUCEY4ZEY6AAURAEG/graph.json","fetch_events":"https://pith.science/api/pith-number/76LS5QBDKFUCEY4ZEY6AAURAEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/action/storage_attestation","attest_author":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/action/author_attestation","sign_citation":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/action/citation_signature","submit_replication":"https://pith.science/pith/76LS5QBDKFUCEY4ZEY6AAURAEG/action/replication_record"}},"created_at":"2026-07-05T11:15:13.128729+00:00","updated_at":"2026-07-05T11:15:13.128729+00:00"}