{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ZTRMEXMKPNX4IGCTXF3HU4TZE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8591e0e7b0662fe180ab8bd79589cca4358426103ad657c12e0f35307ff941b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T08:25:01Z","title_canon_sha256":"10fe33b5d911d46e9177c4dda1e2c24dc3a9c229126c4da36434086af344043a"},"schema_version":"1.0","source":{"id":"2505.19669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19669","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19669v2","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19669","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"2ZTRMEXMKPNX","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"2ZTRMEXMKPNX4IGC","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"2ZTRMEXM","created_at":"2026-07-05T11:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:d7805152980abd78fd6beed3d6bd9c11844d0f10bea2668896aa79e93c0cfa9d","target":"graph","created_at":"2026-07-05T11:14:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.19669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot streaming text-to-speech is an important research topic in human-computer interaction. Existing methods primarily use a lookahead mechanism, relying on future text to achieve natural streaming speech synthesis, which introduces high processing latency. To address this issue, we propose SMLLE, a streaming framework for generating high-quality speech frame-by-frame. SMLLE employs a Transducer to convert text into semantic tokens in real time while simultaneously obtaining duration alignment information. The combined outputs are then fed into a fully autoregressive (AR) streaming model ","authors_text":"Bing Han, Haiyang Sun, Hui Wang, Lingwei Meng, Sheng Zhao, Shujie Hu, Shujie Liu, Yan Lu, Yanmin Qian, Yanqing Liu, Yifan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T08:25:01Z","title":"Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19669","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a7dc6f482d075557bf99b0cb1143c6bbf55004977eba265fe6dc1af70d95798e","target":"record","created_at":"2026-07-05T11:14:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8591e0e7b0662fe180ab8bd79589cca4358426103ad657c12e0f35307ff941b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T08:25:01Z","title_canon_sha256":"10fe33b5d911d46e9177c4dda1e2c24dc3a9c229126c4da36434086af344043a"},"schema_version":"1.0","source":{"id":"2505.19669","kind":"arxiv","version":2}},"canonical_sha256":"d6671612ec53db7e20c29dcbb3d393c930a00e016e32fde066e59293fdcef23b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6671612ec53db7e20c29dcbb3d393c930a00e016e32fde066e59293fdcef23b","first_computed_at":"2026-07-05T11:14:07.907442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:07.907442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SQiXLX2XbHQA3ykus0RUyDZ2SfWIv98wlKKdZJDH+/oigcvjwQQkKF3rTHN3XxQ7rYHruf0kl53Alra8vx3iCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:07.907925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7dc6f482d075557bf99b0cb1143c6bbf55004977eba265fe6dc1af70d95798e","sha256:d7805152980abd78fd6beed3d6bd9c11844d0f10bea2668896aa79e93c0cfa9d"],"state_sha256":"2bdacbf699d06fa20d18d3a5d25884d5a10d8b1e6ca7df9d69894edd44d0708a"}