{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VG3WEXLXLPUK5LZPQ2MKDJJIAH","short_pith_number":"pith:VG3WEXLX","schema_version":"1.0","canonical_sha256":"a9b7625d775be8aeaf2f8698a1a52801f8d2c3d9bce3ec022d066bc5827e28e1","source":{"kind":"arxiv","id":"2402.09378","version":2},"attestation_state":"computed","paper":{"title":"MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hanting Wang, Jialong Zuo, Shengpeng Ji, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-02-14T18:24:41Z","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"},"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":"2402.09378","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-02-14T18:24:41Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"ea7bc8694a2089c41b2a74c259922bd7ab98e68ca5f2068b025edd909f52b85d","abstract_canon_sha256":"d3d46be893762ee4938ce137fea836e730a9b933cd29dab221d8c5d3b0f6b7b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:19.543271Z","signature_b64":"N4WoUjyAegOn5XCbic75SIOVVpLulmudJQj9TADhhKJH7c4x/MrRLTLlGX58wxkgP33tdHh8DW71dzPkYUt4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b7625d775be8aeaf2f8698a1a52801f8d2c3d9bce3ec022d066bc5827e28e1","last_reissued_at":"2026-07-05T08:26:19.542754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:19.542754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hanting Wang, Jialong Zuo, Shengpeng Ji, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-02-14T18:24:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09378","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/2402.09378/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":"2402.09378","created_at":"2026-07-05T08:26:19.542815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09378v2","created_at":"2026-07-05T08:26:19.542815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09378","created_at":"2026-07-05T08:26:19.542815+00:00"},{"alias_kind":"pith_short_12","alias_value":"VG3WEXLXLPUK","created_at":"2026-07-05T08:26:19.542815+00:00"},{"alias_kind":"pith_short_16","alias_value":"VG3WEXLXLPUK5LZP","created_at":"2026-07-05T08:26:19.542815+00:00"},{"alias_kind":"pith_short_8","alias_value":"VG3WEXLX","created_at":"2026-07-05T08:26:19.542815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH","json":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH.json","graph_json":"https://pith.science/api/pith-number/VG3WEXLXLPUK5LZPQ2MKDJJIAH/graph.json","events_json":"https://pith.science/api/pith-number/VG3WEXLXLPUK5LZPQ2MKDJJIAH/events.json","paper":"https://pith.science/paper/VG3WEXLX"},"agent_actions":{"view_html":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH","download_json":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH.json","view_paper":"https://pith.science/paper/VG3WEXLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09378&json=true","fetch_graph":"https://pith.science/api/pith-number/VG3WEXLXLPUK5LZPQ2MKDJJIAH/graph.json","fetch_events":"https://pith.science/api/pith-number/VG3WEXLXLPUK5LZPQ2MKDJJIAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH/action/storage_attestation","attest_author":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH/action/author_attestation","sign_citation":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH/action/citation_signature","submit_replication":"https://pith.science/pith/VG3WEXLXLPUK5LZPQ2MKDJJIAH/action/replication_record"}},"created_at":"2026-07-05T08:26:19.542815+00:00","updated_at":"2026-07-05T08:26:19.542815+00:00"}