{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VG3WEXLXLPUK5LZPQ2MKDJJIAH","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":"d3d46be893762ee4938ce137fea836e730a9b933cd29dab221d8c5d3b0f6b7b6","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-14T18:24:41Z","title_canon_sha256":"ea7bc8694a2089c41b2a74c259922bd7ab98e68ca5f2068b025edd909f52b85d"},"schema_version":"1.0","source":{"id":"2402.09378","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09378","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09378v2","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09378","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"VG3WEXLXLPUK","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"VG3WEXLXLPUK5LZP","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"VG3WEXLX","created_at":"2026-07-05T08:26:19Z"}],"graph_snapshots":[{"event_id":"sha256:0ddbf5dc724651b19503bd3c689faf7639a51e1b0585ccf359cef3ad358e5199","target":"graph","created_at":"2026-07-05T08:26:19Z","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/2402.09378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot text-to-speech (TTS) has gained significant attention due to its powerful voice cloning capabilities, requiring only a few seconds of unseen speaker voice prompts. However, all previous work has been developed for cloud-based systems. Taking autoregressive models as an example, although these approaches achieve high-fidelity voice cloning, they fall short in terms of inference speed, model size, and robustness. Therefore, we propose MobileSpeech, which is a fast, lightweight, and robust zero-shot text-to-speech system based on mobile devices for the first time. Specifically: 1) lever","authors_text":"Hanting Wang, Jialong Zuo, Shengpeng Ji, Zhou Zhao, Ziyue Jiang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-14T18:24:41Z","title":"MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09378","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":"sha256:7e6da12f53fd2d632df50b8ee601fbb245a7575e79cffcba55c48cb42169d6c1","target":"record","created_at":"2026-07-05T08:26:19Z","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":"d3d46be893762ee4938ce137fea836e730a9b933cd29dab221d8c5d3b0f6b7b6","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-14T18:24:41Z","title_canon_sha256":"ea7bc8694a2089c41b2a74c259922bd7ab98e68ca5f2068b025edd909f52b85d"},"schema_version":"1.0","source":{"id":"2402.09378","kind":"arxiv","version":2}},"canonical_sha256":"a9b7625d775be8aeaf2f8698a1a52801f8d2c3d9bce3ec022d066bc5827e28e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9b7625d775be8aeaf2f8698a1a52801f8d2c3d9bce3ec022d066bc5827e28e1","first_computed_at":"2026-07-05T08:26:19.542754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:19.542754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N4WoUjyAegOn5XCbic75SIOVVpLulmudJQj9TADhhKJH7c4x/MrRLTLlGX58wxkgP33tdHh8DW71dzPkYUt4Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:19.543271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09378","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6da12f53fd2d632df50b8ee601fbb245a7575e79cffcba55c48cb42169d6c1","sha256:0ddbf5dc724651b19503bd3c689faf7639a51e1b0585ccf359cef3ad358e5199"],"state_sha256":"049a9c493032a69e21ae540c36660b875fecdb357deea6e0c02562ede97f63e0"}