{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WF2F757CV3ZQKA7IIYFWVUK4NG","short_pith_number":"pith:WF2F757C","schema_version":"1.0","canonical_sha256":"b1745ff7e2aef30503e8460b6ad15c69838d41d42da5e626d869895ab2e37eda","source":{"kind":"arxiv","id":"2501.17332","version":1},"attestation_state":"computed","paper":{"title":"Compact Neural TTS Voices for Accessibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alistair Conkie, Deepanshu Gupta, Eoin Murphy, Jonathan Dyke, Kunal Jain, Petko Petkov, Saumya Shah, Vasilieios Tsiaras","submitted_at":"2025-01-28T22:51:14Z","abstract_excerpt":"Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS) or unit selection (USEL) and (ii) cloud-based neural TTS. SPSS and USEL offer low latency and low disk footprint at the expense of naturalness and audio quality. Cloud-based neural TTS systems provide significantly better audio quality and naturalness but regress in terms of latency and responsiveness, rendering these impractical for real-world applications. More recently, neural TTS models were made deployable to "},"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":"2501.17332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-28T22:51:14Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"cdaed00e505d5823cf240392897bf4fdc9060b1a660373d41ae447e86cf4885f","abstract_canon_sha256":"af56fd9a5154b76c0fe6f0f738aefd7d1b81c047b808e0596cf67e1aa934fa01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:51.411371Z","signature_b64":"iMHh9yAs9j85uUl5I+fqcM995FimE3V9G9z5qggBgG5vy1qgNkmIsy/j1AcLLIjnwh0QvHk3zRuOTMc/PwQmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1745ff7e2aef30503e8460b6ad15c69838d41d42da5e626d869895ab2e37eda","last_reissued_at":"2026-07-05T10:06:51.410924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:51.410924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compact Neural TTS Voices for Accessibility","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alistair Conkie, Deepanshu Gupta, Eoin Murphy, Jonathan Dyke, Kunal Jain, Petko Petkov, Saumya Shah, Vasilieios Tsiaras","submitted_at":"2025-01-28T22:51:14Z","abstract_excerpt":"Contemporary text-to-speech solutions for accessibility applications can typically be classified into two categories: (i) device-based statistical parametric speech synthesis (SPSS) or unit selection (USEL) and (ii) cloud-based neural TTS. SPSS and USEL offer low latency and low disk footprint at the expense of naturalness and audio quality. Cloud-based neural TTS systems provide significantly better audio quality and naturalness but regress in terms of latency and responsiveness, rendering these impractical for real-world applications. More recently, neural TTS models were made deployable to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17332","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/2501.17332/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":"2501.17332","created_at":"2026-07-05T10:06:51.410982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17332v1","created_at":"2026-07-05T10:06:51.410982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17332","created_at":"2026-07-05T10:06:51.410982+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF2F757CV3ZQ","created_at":"2026-07-05T10:06:51.410982+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF2F757CV3ZQKA7I","created_at":"2026-07-05T10:06:51.410982+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF2F757C","created_at":"2026-07-05T10:06:51.410982+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/WF2F757CV3ZQKA7IIYFWVUK4NG","json":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG.json","graph_json":"https://pith.science/api/pith-number/WF2F757CV3ZQKA7IIYFWVUK4NG/graph.json","events_json":"https://pith.science/api/pith-number/WF2F757CV3ZQKA7IIYFWVUK4NG/events.json","paper":"https://pith.science/paper/WF2F757C"},"agent_actions":{"view_html":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG","download_json":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG.json","view_paper":"https://pith.science/paper/WF2F757C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17332&json=true","fetch_graph":"https://pith.science/api/pith-number/WF2F757CV3ZQKA7IIYFWVUK4NG/graph.json","fetch_events":"https://pith.science/api/pith-number/WF2F757CV3ZQKA7IIYFWVUK4NG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG/action/storage_attestation","attest_author":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG/action/author_attestation","sign_citation":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG/action/citation_signature","submit_replication":"https://pith.science/pith/WF2F757CV3ZQKA7IIYFWVUK4NG/action/replication_record"}},"created_at":"2026-07-05T10:06:51.410982+00:00","updated_at":"2026-07-05T10:06:51.410982+00:00"}