{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7B2HHTGAXDXIIT4ATPLHO4A5CW","short_pith_number":"pith:7B2HHTGA","schema_version":"1.0","canonical_sha256":"f87473ccc0b8ee844f809bd677701d158d940986bb506465ac1b0b48fff98c7c","source":{"kind":"arxiv","id":"2403.13353","version":1},"attestation_state":"computed","paper":{"title":"Building speech corpus with diverse voice characteristics for its prompt-based representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aya Watanabe, Detai Xin, Hiroshi Saruwatari, Shinnosuke Takamichi, Wataru Nakata, Yuki Saito","submitted_at":"2024-03-20T07:31:27Z","abstract_excerpt":"In text-to-speech synthesis, the ability to control voice characteristics is vital for various applications. By leveraging thriving text prompt-based generation techniques, it should be possible to enhance the nuanced control of voice characteristics. While previous research has explored the prompt-based manipulation of voice characteristics, most studies have used pre-recorded speech, which limits the diversity of voice characteristics available. Thus, we aim to address this gap by creating a novel corpus and developing a model for prompt-based manipulation of voice characteristics in text-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":"2403.13353","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-20T07:31:27Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d6c3cd9b5da83c9cd70cb872d704f11a03b909833dfbf4ded543d9ce8909dfdf","abstract_canon_sha256":"5cd0000e1e20b77cdde668d99277482916e1c78612b57b092327912037c8fb53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:35.201972Z","signature_b64":"VSfE7LMWQD7UyCcogfvmjQtwooYBjvgUwpKPjxARL7xk6c1XckiabcMGTr7VmlDLfCUkW8TAeudpeJOu65uMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f87473ccc0b8ee844f809bd677701d158d940986bb506465ac1b0b48fff98c7c","last_reissued_at":"2026-07-05T07:58:35.201471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:35.201471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building speech corpus with diverse voice characteristics for its prompt-based representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aya Watanabe, Detai Xin, Hiroshi Saruwatari, Shinnosuke Takamichi, Wataru Nakata, Yuki Saito","submitted_at":"2024-03-20T07:31:27Z","abstract_excerpt":"In text-to-speech synthesis, the ability to control voice characteristics is vital for various applications. By leveraging thriving text prompt-based generation techniques, it should be possible to enhance the nuanced control of voice characteristics. While previous research has explored the prompt-based manipulation of voice characteristics, most studies have used pre-recorded speech, which limits the diversity of voice characteristics available. Thus, we aim to address this gap by creating a novel corpus and developing a model for prompt-based manipulation of voice characteristics in text-to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13353","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/2403.13353/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":"2403.13353","created_at":"2026-07-05T07:58:35.201529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13353v1","created_at":"2026-07-05T07:58:35.201529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13353","created_at":"2026-07-05T07:58:35.201529+00:00"},{"alias_kind":"pith_short_12","alias_value":"7B2HHTGAXDXI","created_at":"2026-07-05T07:58:35.201529+00:00"},{"alias_kind":"pith_short_16","alias_value":"7B2HHTGAXDXIIT4A","created_at":"2026-07-05T07:58:35.201529+00:00"},{"alias_kind":"pith_short_8","alias_value":"7B2HHTGA","created_at":"2026-07-05T07:58:35.201529+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/7B2HHTGAXDXIIT4ATPLHO4A5CW","json":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW.json","graph_json":"https://pith.science/api/pith-number/7B2HHTGAXDXIIT4ATPLHO4A5CW/graph.json","events_json":"https://pith.science/api/pith-number/7B2HHTGAXDXIIT4ATPLHO4A5CW/events.json","paper":"https://pith.science/paper/7B2HHTGA"},"agent_actions":{"view_html":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW","download_json":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW.json","view_paper":"https://pith.science/paper/7B2HHTGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13353&json=true","fetch_graph":"https://pith.science/api/pith-number/7B2HHTGAXDXIIT4ATPLHO4A5CW/graph.json","fetch_events":"https://pith.science/api/pith-number/7B2HHTGAXDXIIT4ATPLHO4A5CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW/action/storage_attestation","attest_author":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW/action/author_attestation","sign_citation":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW/action/citation_signature","submit_replication":"https://pith.science/pith/7B2HHTGAXDXIIT4ATPLHO4A5CW/action/replication_record"}},"created_at":"2026-07-05T07:58:35.201529+00:00","updated_at":"2026-07-05T07:58:35.201529+00:00"}