{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ZTRMEXMKPNX4IGCTXF3HU4TZE","short_pith_number":"pith:2ZTRMEXM","schema_version":"1.0","canonical_sha256":"d6671612ec53db7e20c29dcbb3d393c930a00e016e32fde066e59293fdcef23b","source":{"kind":"arxiv","id":"2505.19669","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bing Han, Haiyang Sun, Hui Wang, Lingwei Meng, Sheng Zhao, Shujie Hu, Shujie Liu, Yan Lu, Yanmin Qian, Yanqing Liu, Yifan Yang","submitted_at":"2025-05-26T08:25:01Z","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 "},"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":"2505.19669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T08:25:01Z","cross_cats_sorted":[],"title_canon_sha256":"10fe33b5d911d46e9177c4dda1e2c24dc3a9c229126c4da36434086af344043a","abstract_canon_sha256":"8591e0e7b0662fe180ab8bd79589cca4358426103ad657c12e0f35307ff941b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:07.907925Z","signature_b64":"SQiXLX2XbHQA3ykus0RUyDZ2SfWIv98wlKKdZJDH+/oigcvjwQQkKF3rTHN3XxQ7rYHruf0kl53Alra8vx3iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6671612ec53db7e20c29dcbb3d393c930a00e016e32fde066e59293fdcef23b","last_reissued_at":"2026-07-05T11:14:07.907442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:07.907442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Streaming Text to Speech Synthesis with Transducer and Auto-Regressive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bing Han, Haiyang Sun, Hui Wang, Lingwei Meng, Sheng Zhao, Shujie Hu, Shujie Liu, Yan Lu, Yanmin Qian, Yanqing Liu, Yifan Yang","submitted_at":"2025-05-26T08:25:01Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19669","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/2505.19669/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":"2505.19669","created_at":"2026-07-05T11:14:07.907501+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19669v2","created_at":"2026-07-05T11:14:07.907501+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19669","created_at":"2026-07-05T11:14:07.907501+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZTRMEXMKPNX","created_at":"2026-07-05T11:14:07.907501+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZTRMEXMKPNX4IGC","created_at":"2026-07-05T11:14:07.907501+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZTRMEXM","created_at":"2026-07-05T11:14:07.907501+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22746","citing_title":"Next Tokens Denoising for Speech Synthesis","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE","json":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE.json","graph_json":"https://pith.science/api/pith-number/2ZTRMEXMKPNX4IGCTXF3HU4TZE/graph.json","events_json":"https://pith.science/api/pith-number/2ZTRMEXMKPNX4IGCTXF3HU4TZE/events.json","paper":"https://pith.science/paper/2ZTRMEXM"},"agent_actions":{"view_html":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE","download_json":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE.json","view_paper":"https://pith.science/paper/2ZTRMEXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19669&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZTRMEXMKPNX4IGCTXF3HU4TZE/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZTRMEXMKPNX4IGCTXF3HU4TZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/action/storage_attestation","attest_author":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/action/author_attestation","sign_citation":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/action/citation_signature","submit_replication":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/action/replication_record"}},"created_at":"2026-07-05T11:14:07.907501+00:00","updated_at":"2026-07-05T11:14:07.907501+00:00"}