{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2ZTRMEXMKPNX4IGCTXF3HU4TZE","short_pith_number":"pith:2ZTRMEXM","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"},"canonical_sha256":"d6671612ec53db7e20c29dcbb3d393c930a00e016e32fde066e59293fdcef23b","source":{"kind":"arxiv","id":"2505.19669","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2ZTRMEXMKPNX4IGCTXF3HU4TZE","target":"record","payload":{"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"},"canonical_sha256":"d6671612ec53db7e20c29dcbb3d393c930a00e016e32fde066e59293fdcef23b","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"},"source_kind":"arxiv","source_id":"2505.19669","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwRVhdjQF1Rr2AK0dTnIYvfG8AohhFlgMrHREYZlSESJ81ciwzykq4aXrydKasO+o5xmpSCDvdaUoYc7H7yBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:00:17.876719Z"},"content_sha256":"a7dc6f482d075557bf99b0cb1143c6bbf55004977eba265fe6dc1af70d95798e","schema_version":"1.0","event_id":"sha256:a7dc6f482d075557bf99b0cb1143c6bbf55004977eba265fe6dc1af70d95798e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2ZTRMEXMKPNX4IGCTXF3HU4TZE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yj5+PIGZdiMnhVwnfOMdznWdO32U0XJMdJ/Uol66pXP9xISQXTIjTPvkrFEgwOcg6+mXjXIvJIXKkF0zUi0qCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:00:17.877671Z"},"content_sha256":"d7805152980abd78fd6beed3d6bd9c11844d0f10bea2668896aa79e93c0cfa9d","schema_version":"1.0","event_id":"sha256:d7805152980abd78fd6beed3d6bd9c11844d0f10bea2668896aa79e93c0cfa9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/bundle.json","state_url":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T03:00:17Z","links":{"resolver":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE","bundle":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/bundle.json","state":"https://pith.science/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ZTRMEXMKPNX4IGCTXF3HU4TZE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/kJl+/Uu5WOCwVuPkWmx/fm0yX9kWY+OxZ2pieIg3Dxb/08EI3K0t/iWiBdvQp7VoWbAMGULHtcZhsTDNU5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:00:17.894345Z","bundle_sha256":"c8326f56a2a6ee0ff75bd4ff546d99cfd3e204c89f7e1d1b426896d132767909"}}