{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4AKE4OH4DWNQXSB5CK43DAYLE","short_pith_number":"pith:T4AKE4OH","schema_version":"1.0","canonical_sha256":"9f00a271c7e0ecd85e41e895cd8c185922ca179c2aaf6eb315e40760b0feaa7d","source":{"kind":"arxiv","id":"2408.12170","version":1},"attestation_state":"computed","paper":{"title":"VoiceX: A Text-To-Speech Framework for Custom Voices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Daksitha Withanage Don, Elisabeth Andr\\'e, Johanna Kuch, Otto Grothe, Ruben Schlagowski, Silvan Mertes","submitted_at":"2024-08-22T07:32:32Z","abstract_excerpt":"Modern TTS systems are capable of creating highly realistic and natural-sounding speech. Despite these developments, the process of customizing TTS voices remains a complex task, mostly requiring the expertise of specialists within the field. One reason for this is the utilization of deep learning models, which are characterized by their expansive, non-interpretable parameter spaces, restricting the feasibility of manual customization. In this paper, we present a novel human-in-the-loop paradigm based on an evolutionary algorithm for directly interacting with the parameter space of a neural TT"},"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":"2408.12170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-08-22T07:32:32Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9a8f1efdfca30ecefc5e4935b7d9970a74d5bb6afed5a31a8d7c88cc9108f482","abstract_canon_sha256":"9e9287f39f6f8cdabb77280c5e91e6ae86ef56b061e0d92dc5cc592ef8a120f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:05.174784Z","signature_b64":"kVuX4uFFoKlaLitWY5l5VRFe1DSyORkotKWW9whF1Gl6vY6vHOMC1Vbsxq10exNBZN0pFpQVMJ/spj/TUP/jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f00a271c7e0ecd85e41e895cd8c185922ca179c2aaf6eb315e40760b0feaa7d","last_reissued_at":"2026-07-05T08:58:05.174362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:05.174362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoiceX: A Text-To-Speech Framework for Custom Voices","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.HC","authors_text":"Daksitha Withanage Don, Elisabeth Andr\\'e, Johanna Kuch, Otto Grothe, Ruben Schlagowski, Silvan Mertes","submitted_at":"2024-08-22T07:32:32Z","abstract_excerpt":"Modern TTS systems are capable of creating highly realistic and natural-sounding speech. Despite these developments, the process of customizing TTS voices remains a complex task, mostly requiring the expertise of specialists within the field. One reason for this is the utilization of deep learning models, which are characterized by their expansive, non-interpretable parameter spaces, restricting the feasibility of manual customization. In this paper, we present a novel human-in-the-loop paradigm based on an evolutionary algorithm for directly interacting with the parameter space of a neural TT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12170","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/2408.12170/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":"2408.12170","created_at":"2026-07-05T08:58:05.174432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12170v1","created_at":"2026-07-05T08:58:05.174432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12170","created_at":"2026-07-05T08:58:05.174432+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4AKE4OH4DWN","created_at":"2026-07-05T08:58:05.174432+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4AKE4OH4DWNQXSB","created_at":"2026-07-05T08:58:05.174432+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4AKE4OH","created_at":"2026-07-05T08:58:05.174432+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/T4AKE4OH4DWNQXSB5CK43DAYLE","json":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE.json","graph_json":"https://pith.science/api/pith-number/T4AKE4OH4DWNQXSB5CK43DAYLE/graph.json","events_json":"https://pith.science/api/pith-number/T4AKE4OH4DWNQXSB5CK43DAYLE/events.json","paper":"https://pith.science/paper/T4AKE4OH"},"agent_actions":{"view_html":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE","download_json":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE.json","view_paper":"https://pith.science/paper/T4AKE4OH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12170&json=true","fetch_graph":"https://pith.science/api/pith-number/T4AKE4OH4DWNQXSB5CK43DAYLE/graph.json","fetch_events":"https://pith.science/api/pith-number/T4AKE4OH4DWNQXSB5CK43DAYLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE/action/storage_attestation","attest_author":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE/action/author_attestation","sign_citation":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE/action/citation_signature","submit_replication":"https://pith.science/pith/T4AKE4OH4DWNQXSB5CK43DAYLE/action/replication_record"}},"created_at":"2026-07-05T08:58:05.174432+00:00","updated_at":"2026-07-05T08:58:05.174432+00:00"}