{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GMPLL7XY7PUQ2DPY3YUGUAYLV7","short_pith_number":"pith:GMPLL7XY","schema_version":"1.0","canonical_sha256":"331eb5fef8fbe90d0df8de286a030bafc2932650ff5e5d9f8a3b9c4634de9134","source":{"kind":"arxiv","id":"2607.23938","version":1},"attestation_state":"computed","paper":{"title":"Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bajian Xiang, Cheng Wen, Han Zhao, Hao Wang, Haoxu Wang, Jiawei Jin, Jiayan Cui, Jie Chen, Mengxi Nie, Tianyu Zhao, Weiqin Li, Xiangang Li, Xiang Lv, Yang Xiang, Yang Zhou","submitted_at":"2026-07-27T02:30:15Z","abstract_excerpt":"In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, audio quality, controllability, multilingual coverage, efficiency, and robustness. It combines a 12.5~Hz low-frame-rate speech tokenizer for reduced inference latency with a five-stage progressive training paradigm for coordinated language model (LM) and flow-matching model (FM) optimization. The model provides production-level control through free-style natural-language instructions and fine-grained inline tags, while"},"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":"2607.23938","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-27T02:30:15Z","cross_cats_sorted":[],"title_canon_sha256":"a4a8406d6d9224effbc997ed9eafc60e83608c9fd1ae06c63bdd5357e21f8e58","abstract_canon_sha256":"928df71286ff53368ac4c5eb52dd2ade45d136e5b0fc0c6de8ec96b43912d056"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:36.763419Z","signature_b64":"xXMFuPnd8433Vg06DSeMEYf/U8GDmCISGoHf8fOhOcEaIPbwikXB/A3WGDpKW7IBYpdgJ2olZRvpH8tpdkihBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"331eb5fef8fbe90d0df8de286a030bafc2932650ff5e5d9f8a3b9c4634de9134","last_reissued_at":"2026-07-28T01:23:36.762581Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:36.762581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Qwen-Audio-3.0-TTS: Freely Controllable and Highly Robust Speech Synthesis with Multi-Stage Training Paradigm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bajian Xiang, Cheng Wen, Han Zhao, Hao Wang, Haoxu Wang, Jiawei Jin, Jiayan Cui, Jie Chen, Mengxi Nie, Tianyu Zhao, Weiqin Li, Xiangang Li, Xiang Lv, Yang Xiang, Yang Zhou","submitted_at":"2026-07-27T02:30:15Z","abstract_excerpt":"In this report, we present Qwen-Audio-3.0-TTS, a production-oriented speech synthesis system that jointly advances content consistency, speaker similarity, prosodic naturalness, audio quality, controllability, multilingual coverage, efficiency, and robustness. It combines a 12.5~Hz low-frame-rate speech tokenizer for reduced inference latency with a five-stage progressive training paradigm for coordinated language model (LM) and flow-matching model (FM) optimization. The model provides production-level control through free-style natural-language instructions and fine-grained inline tags, while"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23938","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/2607.23938/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":"2607.23938","created_at":"2026-07-28T01:23:36.763003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23938v1","created_at":"2026-07-28T01:23:36.763003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23938","created_at":"2026-07-28T01:23:36.763003+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMPLL7XY7PUQ","created_at":"2026-07-28T01:23:36.763003+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMPLL7XY7PUQ2DPY","created_at":"2026-07-28T01:23:36.763003+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMPLL7XY","created_at":"2026-07-28T01:23:36.763003+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/GMPLL7XY7PUQ2DPY3YUGUAYLV7","json":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7.json","graph_json":"https://pith.science/api/pith-number/GMPLL7XY7PUQ2DPY3YUGUAYLV7/graph.json","events_json":"https://pith.science/api/pith-number/GMPLL7XY7PUQ2DPY3YUGUAYLV7/events.json","paper":"https://pith.science/paper/GMPLL7XY"},"agent_actions":{"view_html":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7","download_json":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7.json","view_paper":"https://pith.science/paper/GMPLL7XY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23938&json=true","fetch_graph":"https://pith.science/api/pith-number/GMPLL7XY7PUQ2DPY3YUGUAYLV7/graph.json","fetch_events":"https://pith.science/api/pith-number/GMPLL7XY7PUQ2DPY3YUGUAYLV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7/action/storage_attestation","attest_author":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7/action/author_attestation","sign_citation":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7/action/citation_signature","submit_replication":"https://pith.science/pith/GMPLL7XY7PUQ2DPY3YUGUAYLV7/action/replication_record"}},"created_at":"2026-07-28T01:23:36.763003+00:00","updated_at":"2026-07-28T01:23:36.763003+00:00"}