{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4TCX6I3DYP6EC2J7ALBIPJVLAL","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":"93f6be23f42f0988ec1d43a613b7a8104bcd7385adf8d80f752d113d06cd3d76","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T16:11:10Z","title_canon_sha256":"17f0a57bf0884798557cd081c86fc3e30d3acdc1a8215e3d1a1697765e24206b"},"schema_version":"1.0","source":{"id":"2505.19206","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19206","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19206v1","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19206","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_12","alias_value":"4TCX6I3DYP6E","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_16","alias_value":"4TCX6I3DYP6EC2J7","created_at":"2026-07-05T11:09:26Z"},{"alias_kind":"pith_short_8","alias_value":"4TCX6I3D","created_at":"2026-07-05T11:09:26Z"}],"graph_snapshots":[{"event_id":"sha256:fcf76a26581ed9c873a9305f08f8b565d46caf13ff8e39f05152c9931683e62f","target":"graph","created_at":"2026-07-05T11:09:26Z","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/2505.19206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The latency bottleneck of traditional text-to-speech (TTS) systems fundamentally hinders the potential of streaming large language models (LLMs) in conversational AI. These TTS systems, typically trained and inferenced on complete utterances, introduce unacceptable delays, even with optimized inference speeds, when coupled with streaming LLM outputs. This is particularly problematic for creating responsive conversational agents where low first-token latency is critical. In this paper, we present SpeakStream, a streaming TTS system that generates audio incrementally from streaming text using a ","authors_text":"Navdeep Jaitly, Richard He Bai, Tatiana Likhomanenko, Zijin Gu","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T16:11:10Z","title":"SpeakStream: Streaming Text-to-Speech with Interleaved Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19206","kind":"arxiv","version":1},"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:e8188011927a939d6d3ebcc0d0adcd2cc8b369894cc44abfc3323999d104942a","target":"record","created_at":"2026-07-05T11:09:26Z","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":"93f6be23f42f0988ec1d43a613b7a8104bcd7385adf8d80f752d113d06cd3d76","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T16:11:10Z","title_canon_sha256":"17f0a57bf0884798557cd081c86fc3e30d3acdc1a8215e3d1a1697765e24206b"},"schema_version":"1.0","source":{"id":"2505.19206","kind":"arxiv","version":1}},"canonical_sha256":"e4c57f2363c3fc41693f02c287a6ab02d8d7bddb714f3f2d0fbee7beec949bfe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4c57f2363c3fc41693f02c287a6ab02d8d7bddb714f3f2d0fbee7beec949bfe","first_computed_at":"2026-07-05T11:09:26.414330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:26.414330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eqr9581jMW2jD+5aCCDXXni2d2EkTNNdk0wIATogqw2J+l3n0cfi/c6NCQ/aK6CzfGQLR/UEafAb5+crrJKqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:26.414813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19206","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8188011927a939d6d3ebcc0d0adcd2cc8b369894cc44abfc3323999d104942a","sha256:fcf76a26581ed9c873a9305f08f8b565d46caf13ff8e39f05152c9931683e62f"],"state_sha256":"242af0df18134943d45c16640d579c3a3c6d1574bd42460429af2e899a0e3a2a"}