{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VSKR2XGK3VYDWSHZAX7H4425XG","short_pith_number":"pith:VSKR2XGK","schema_version":"1.0","canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","source":{"kind":"arxiv","id":"2606.21882","version":1},"attestation_state":"computed","paper":{"title":"Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Jason Roche, Junjie Lai, Muyang Du","submitted_at":"2026-06-20T04:47:45Z","abstract_excerpt":"Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TTS, a streaming variant of T5-TTS that enables low-latency, word-by-word incremental speech synthesis through encoder-decoder language modeling and monotonic alignment learning. S5-TTS begins generating speech immediately after receiving the first few words, substantially reducing end-to-end response latency. To maintain quality under limited lookahead, we introduce a lookahead-causal masking mechanism with Conv-based"},"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":"2606.21882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-20T04:47:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"983515e98079492cec282a3045e9a6f44072815bcad18c23291801362153f5b4","abstract_canon_sha256":"994d9090f8be06ea1b9f7c9b5e0df0fd6849975287fe4b171a66775e731dea57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:01.809629Z","signature_b64":"7jcDpvg0ScZFIyH26jQf6rpS4E3y90Pr0Msle3C7EOI9UZbm6PauOXjCMYPsy4EQw/G8PyqMsZ1NjneIC93TAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac951d5ccadd703b48f905fe7e735db983a1337714eb710054be0c8ef6718def","last_reissued_at":"2026-06-23T02:13:01.809256Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:01.809256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Jason Roche, Junjie Lai, Muyang Du","submitted_at":"2026-06-20T04:47:45Z","abstract_excerpt":"Streaming text-to-speech synthesis in cascaded LLM-TTS systems still faces latency challenges as most TTS models require full context before initiating generation. We present S5-TTS, a streaming variant of T5-TTS that enables low-latency, word-by-word incremental speech synthesis through encoder-decoder language modeling and monotonic alignment learning. S5-TTS begins generating speech immediately after receiving the first few words, substantially reducing end-to-end response latency. To maintain quality under limited lookahead, we introduce a lookahead-causal masking mechanism with Conv-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21882","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/2606.21882/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":"2606.21882","created_at":"2026-06-23T02:13:01.809320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21882v1","created_at":"2026-06-23T02:13:01.809320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21882","created_at":"2026-06-23T02:13:01.809320+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSKR2XGK3VYD","created_at":"2026-06-23T02:13:01.809320+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSKR2XGK3VYDWSHZ","created_at":"2026-06-23T02:13:01.809320+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSKR2XGK","created_at":"2026-06-23T02:13:01.809320+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/VSKR2XGK3VYDWSHZAX7H4425XG","json":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG.json","graph_json":"https://pith.science/api/pith-number/VSKR2XGK3VYDWSHZAX7H4425XG/graph.json","events_json":"https://pith.science/api/pith-number/VSKR2XGK3VYDWSHZAX7H4425XG/events.json","paper":"https://pith.science/paper/VSKR2XGK"},"agent_actions":{"view_html":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG","download_json":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG.json","view_paper":"https://pith.science/paper/VSKR2XGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21882&json=true","fetch_graph":"https://pith.science/api/pith-number/VSKR2XGK3VYDWSHZAX7H4425XG/graph.json","fetch_events":"https://pith.science/api/pith-number/VSKR2XGK3VYDWSHZAX7H4425XG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/action/storage_attestation","attest_author":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/action/author_attestation","sign_citation":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/action/citation_signature","submit_replication":"https://pith.science/pith/VSKR2XGK3VYDWSHZAX7H4425XG/action/replication_record"}},"created_at":"2026-06-23T02:13:01.809320+00:00","updated_at":"2026-06-23T02:13:01.809320+00:00"}