{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2NENJFGICL6JUJ4LLQLBD4J6CP","short_pith_number":"pith:2NENJFGI","schema_version":"1.0","canonical_sha256":"d348d494c812fc9a278b5c1611f13e13ebf77a99e7a632ef429e1e3fa6f90489","source":{"kind":"arxiv","id":"2410.00767","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Text-to-Speech from Continuous Text Streams","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"David Aponte, Dung Tran, Kazuhito Koishida, Tianyi Chen, Trung Dang","submitted_at":"2024-10-01T15:04:21Z","abstract_excerpt":"Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive continuously in short chunks, necessitating instant responses from the system. We identify the essential capabilities required for chunk-level streaming and introduce LiveSpeech 2, a stream-aware model that supports infinitely long speech generation, text-audio stream synchronization, and seamless transitions between short speech chunks. To achieve these, we propos"},"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":"2410.00767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-01T15:04:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0a4d5f176ae79d9296c8064e1bf4f40b227f742fc15bb517cff1daf5eca2513c","abstract_canon_sha256":"2f94b686ad5aff177555d6c0b5086b25bce29981a7561d5f733b16e190460611"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:10.353075Z","signature_b64":"2BerAOjS+XBoAJia7llDwhzocmt69MYu03sLkbbY9/1sGUh0hzlSpq0L0KmzSuCle/HrDalwNpxmGgCR5JHcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d348d494c812fc9a278b5c1611f13e13ebf77a99e7a632ef429e1e3fa6f90489","last_reissued_at":"2026-07-05T09:14:10.352675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:10.352675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Text-to-Speech from Continuous Text Streams","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"David Aponte, Dung Tran, Kazuhito Koishida, Tianyi Chen, Trung Dang","submitted_at":"2024-10-01T15:04:21Z","abstract_excerpt":"Existing zero-shot text-to-speech (TTS) systems are typically designed to process complete sentences and are constrained by the maximum duration for which they have been trained. However, in many streaming applications, texts arrive continuously in short chunks, necessitating instant responses from the system. We identify the essential capabilities required for chunk-level streaming and introduce LiveSpeech 2, a stream-aware model that supports infinitely long speech generation, text-audio stream synchronization, and seamless transitions between short speech chunks. To achieve these, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00767","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/2410.00767/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":"2410.00767","created_at":"2026-07-05T09:14:10.352730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.00767v1","created_at":"2026-07-05T09:14:10.352730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00767","created_at":"2026-07-05T09:14:10.352730+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NENJFGICL6J","created_at":"2026-07-05T09:14:10.352730+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NENJFGICL6JUJ4L","created_at":"2026-07-05T09:14:10.352730+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NENJFGI","created_at":"2026-07-05T09:14:10.352730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.10117","citing_title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP","json":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP.json","graph_json":"https://pith.science/api/pith-number/2NENJFGICL6JUJ4LLQLBD4J6CP/graph.json","events_json":"https://pith.science/api/pith-number/2NENJFGICL6JUJ4LLQLBD4J6CP/events.json","paper":"https://pith.science/paper/2NENJFGI"},"agent_actions":{"view_html":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP","download_json":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP.json","view_paper":"https://pith.science/paper/2NENJFGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.00767&json=true","fetch_graph":"https://pith.science/api/pith-number/2NENJFGICL6JUJ4LLQLBD4J6CP/graph.json","fetch_events":"https://pith.science/api/pith-number/2NENJFGICL6JUJ4LLQLBD4J6CP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP/action/storage_attestation","attest_author":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP/action/author_attestation","sign_citation":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP/action/citation_signature","submit_replication":"https://pith.science/pith/2NENJFGICL6JUJ4LLQLBD4J6CP/action/replication_record"}},"created_at":"2026-07-05T09:14:10.352730+00:00","updated_at":"2026-07-05T09:14:10.352730+00:00"}