{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VDHPDHEJUHJPVTIOJ75F7NEXJB","short_pith_number":"pith:VDHPDHEJ","schema_version":"1.0","canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","source":{"kind":"arxiv","id":"2608.11737","version":1},"attestation_state":"computed","paper":{"title":"Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daiyu Huang, Hua Chai, Junbo Li, Jun Fang, Naiqiang Tan, Peijie Chen, Qingyang Hong, Weijie Wu, Yiming Liu, Zhipeng Nie, Zhuanling Zha","submitted_at":"2026-08-12T07:23:54Z","abstract_excerpt":"In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning objectives. However, due to the inherent nature of speech, semantic and acoustic information cannot be completely decoupled, and ASR-based tokenizers discard acoustic details to focus on linguistic content; models relying on them usually struggle to achieve optimal speaker similarity. Furthermore, these tokenizers are optimized independently and lack direct supervision from downstream acoustic generation tasks. This isol"},"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":"2608.11737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-12T07:23:54Z","cross_cats_sorted":[],"title_canon_sha256":"18531b11d99f3cfccfd0fe945eb1f809e56e8d61522121afee0cffaad419c7ac","abstract_canon_sha256":"257e5903daef31cf07d2af03fa353fd83280403b4335abdfe69d917c0d463ba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:27:58.077271Z","signature_b64":"YHHAa5OBSHCBsWzeBOKcsphxVTmEbwHV04NEdRWpUgYndSzSzXi38XdsAIRIeQsgjGQUJMH7t69n29onADdWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8cef19c89a1d2facd0e4ffa5fb497486921688d4e9262ae6978a54d47ab9e04","last_reissued_at":"2026-08-13T01:27:58.074193Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:27:58.074193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Daiyu Huang, Hua Chai, Junbo Li, Jun Fang, Naiqiang Tan, Peijie Chen, Qingyang Hong, Weijie Wu, Yiming Liu, Zhipeng Nie, Zhuanling Zha","submitted_at":"2026-08-12T07:23:54Z","abstract_excerpt":"In current zero-shot text-to-speech systems, conventional semantic tokenizers are typically optimized using supervised automatic speech recognition or self-supervised learning objectives. However, due to the inherent nature of speech, semantic and acoustic information cannot be completely decoupled, and ASR-based tokenizers discard acoustic details to focus on linguistic content; models relying on them usually struggle to achieve optimal speaker similarity. Furthermore, these tokenizers are optimized independently and lack direct supervision from downstream acoustic generation tasks. This isol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11737","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/2608.11737/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":"2608.11737","created_at":"2026-08-13T01:27:58.075630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11737v1","created_at":"2026-08-13T01:27:58.075630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11737","created_at":"2026-08-13T01:27:58.075630+00:00"},{"alias_kind":"pith_short_12","alias_value":"VDHPDHEJUHJP","created_at":"2026-08-13T01:27:58.075630+00:00"},{"alias_kind":"pith_short_16","alias_value":"VDHPDHEJUHJPVTIO","created_at":"2026-08-13T01:27:58.075630+00:00"},{"alias_kind":"pith_short_8","alias_value":"VDHPDHEJ","created_at":"2026-08-13T01:27:58.075630+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/VDHPDHEJUHJPVTIOJ75F7NEXJB","json":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB.json","graph_json":"https://pith.science/api/pith-number/VDHPDHEJUHJPVTIOJ75F7NEXJB/graph.json","events_json":"https://pith.science/api/pith-number/VDHPDHEJUHJPVTIOJ75F7NEXJB/events.json","paper":"https://pith.science/paper/VDHPDHEJ"},"agent_actions":{"view_html":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB","download_json":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB.json","view_paper":"https://pith.science/paper/VDHPDHEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11737&json=true","fetch_graph":"https://pith.science/api/pith-number/VDHPDHEJUHJPVTIOJ75F7NEXJB/graph.json","fetch_events":"https://pith.science/api/pith-number/VDHPDHEJUHJPVTIOJ75F7NEXJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/action/storage_attestation","attest_author":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/action/author_attestation","sign_citation":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/action/citation_signature","submit_replication":"https://pith.science/pith/VDHPDHEJUHJPVTIOJ75F7NEXJB/action/replication_record"}},"created_at":"2026-08-13T01:27:58.075630+00:00","updated_at":"2026-08-13T01:27:58.075630+00:00"}